© 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. 8297
    Prev
    Next
    INDEX
    Explanations

    references to legal cases or statutory provisions

    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
    ChildScrollView
    -0.69
     ModelExpression
    -0.66
     sanitaires
    -0.57
    ioutil
    -0.56
     становника
    -0.56
    Πηγές
    -0.55
     culturelles
    -0.55
    Hentet
    -0.54
    setVerticalGroup
    -0.54
     שוליים
    -0.53
    POSITIVE LOGITS
    <bos>
    0.77
     Италијани
    0.61
    DebuggerNonUser
    0.56
    !*\
    0.55
     /\.(
    0.55
    NamedQueries
    0.54
    انيف
    0.52
    Geplaatst
    0.52
    dafx
    0.51
    GeoNames
    0.51
    Activations Density 0.060%

    No Known Activations