© 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. 2544
    Prev
    Next
    INDEX
    Explanations

    phrases related to diminishing or declining states

    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
    +0.25
    0.9%
    1036
    +0.10
    0.4%
    486
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1036
    +0.25
    0.02
    135
    +0.10
    0.03
    335
    +0.09
    0.04
    Negative Logits
    <bos>
    -1.95
     intersper
    -1.19
     fuf
    -1.00
     suscep
    -0.96
     encomp
    -0.89
     endow
    -0.82
     gratify
    -0.81
     disagre
    -0.80
     ?...
    -0.78
     purcha
    -0.77
    POSITIVE LOGITS
     increasingly
    0.85
     Increasing
    0.74
    Increasing
    0.72
    increasing
    0.71
     increasing
    0.70
     kuan
    0.67
     progressively
    0.64
    arkhand
    0.63
    =>'
    0.61
     decreasing
    0.61
    Activations Density 0.397%

    No Known Activations