© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2722
    Prev
    Next
    INDEX
    Explanations

    instances of the word "undermine" and its variations, indicating a focus on actions or behaviors that weaken or sabotage something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    1.3%
    1909
    +0.10
    0.5%
    161
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1142
    +0.24
    0.02
    147
    +0.10
    0.01
    1616
    +0.09
    0.01
    Negative Logits
    <bos>
    -3.23
    /***
    -0.78
    Kanpo
    -0.70
    arr
    -0.70
    /*!
    -0.69
    setClass
    -0.67
    //{
    -0.66
    api
    -0.66
     finally
    -0.64
     enter
    -0.63
    POSITIVE LOGITS
     stockholm
    1.73
     jaya
    1.60
     Minang
    1.60
     bandung
    1.58
     dises
    1.56
     aen
    1.50
     toledo
    1.49
     ecru
    1.48
     lele
    1.47
     fta
    1.47
    Activations Density 0.054%

    No Known Activations