© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20101
    Prev
    Next
    INDEX
    Explanations

    mentions of percentages and their implications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    談社
    -0.95
     roulant
    -0.88
     uſe
    -0.87
     himſelf
    -0.86
     raiſ
    -0.85
     pleaſure
    -0.85
     Efq
    -0.83
     uſed
    -0.81
     cauſe
    -0.80
     caufe
    -0.76
    POSITIVE LOGITS
    mybatisplus
    0.88
    hdashline
    0.77
    bigoplus
    0.73
    ment
    0.72
    ią
    0.71
    en
    0.69
     Prozent
    0.69
     trent
    0.69
    '));
    0.68
     Chaudh
    0.67
    Activations Density 0.011%

    No Known Activations