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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7240
    Prev
    Next
    INDEX
    Explanations

    phrases related to debates or contrasting situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1177
    +0.15
    0.5%
    50
    +0.15
    0.5%
    1741
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1288
    +0.15
    0.08
    1265
    +0.15
    0.05
    1041
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.00
    ⓧ
    -0.88
    <?
    -0.76
    
    -0.68
    /**
    -0.63
    Lmfao
    -0.62
    /*
    -0.55
    Transkript
    -0.55
    FTFY
    -0.52
    /***
    -0.52
    POSITIVE LOGITS
     lele
    0.89
     antik
    0.83
     accla
    0.82
     kasa
    0.78
     maksi
    0.77
     mef
    0.77
     ineffec
    0.77
     maneu
    0.76
     kram
    0.76
     saba
    0.76
    Activations Density 0.747%

    No Known Activations