© 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. 2595
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Ant" followed by a number

    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
    410
    +0.11
    0.4%
    1806
    +0.10
    0.4%
    795
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    795
    +0.11
    0.03
    1806
    +0.10
    0.03
    890
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.58
    TextHelper
    -0.72
    ValueGenerated
    -0.70
    protected
    -0.69
    cshtml
    -0.69
    pexpr
    -0.69
    GroupLayout
    -0.66
    PMailer
    -0.65
    Архівовано
    -0.64
    EndInit
    -0.64
    POSITIVE LOGITS
     maneu
    2.09
     shenan
    1.95
     increa
    1.92
     reluct
    1.90
     impra
    1.87
     stockholm
    1.86
     affor
    1.85
     fortn
    1.85
     emphat
    1.84
     strick
    1.80
    Activations Density 0.192%

    No Known Activations