© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2564
    Prev
    Next
    INDEX
    Explanations

    instances where the word "unless" is mentioned

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.10
    0.4%
    1974
    +0.07
    0.3%
    2036
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1755
    +0.10
    0.03
    2036
    +0.07
    0.03
    314
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.29
    ///**
    -0.83
    
    -0.74
    public
    -0.73
    /**
    -0.73
     finally
    -0.72
    finally
    -0.72
    addComponent
    -0.70
    export
    -0.70
    /*
    -0.69
    POSITIVE LOGITS
     maneu
    2.10
     stockholm
    1.89
     Unless
    1.83
     affor
    1.82
     unless
    1.80
     shenan
    1.76
     ibiza
    1.76
     bandung
    1.75
     frankfurt
    1.75
    unless
    1.74
    Activations Density 0.072%

    No Known Activations