© 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. 31043
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and codes related to files, citations, and organizational structure

    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
    ftagPool
    -0.75
     productName
    -0.66
    principalColumn
    -0.63
     Heywood
    -0.61
    IntoConstraints
    -0.60
     purpoſe
    -0.60
    GEBURTSDATUM
    -0.57
     necessariamente
    -0.57
     Immutable
    -0.56
    NameInMap
    -0.56
    POSITIVE LOGITS
    Tikang
    0.58
     rare
    0.56
     mixed
    0.52
    vastatin
    0.48
     .
    0.47
    <bos>
    0.47
     ред
    0.47
    tzmann
    0.47
    vas
    0.46
    jemah
    0.46
    Activations Density 0.095%

    No Known Activations