© 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. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26623
    Prev
    Next
    INDEX
    Explanations

    references to studies and their purposes

    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
    Билгалдахарш
    -0.72
    Izvori
    -0.58
    propTypes
    -0.57
     privilégi
    -0.57
    WireFormatLite
    -0.52
     informée
    -0.52
     pakan
    -0.50
    ɚ
    -0.50
     privilegi
    -0.50
    alni
    -0.49
    POSITIVE LOGITS
    ThroughAttribute
    0.65
    libft
    0.59
    发表于
    0.58
    Tikang
    0.57
     nahilalakip
    0.55
    lismo
    0.53
    المناصب
    0.53
    DoubleQuotes
    0.53
    úrate
    0.52
     Jovi
    0.52
    Activations Density 0.008%

    No Known Activations