© 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. 8712
    Prev
    Next
    INDEX
    Explanations

    numerical data, specifically dates and scores related to sports events

    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
     yourselves
    -0.58
    графі
    -0.54
    Diaz
    -0.52
    ativité
    -0.52
    ніципа
    -0.50
     ninjas
    -0.50
    niająca
    -0.50
     ourselves
    -0.48
     Schult
    -0.47
    NgModule
    -0.47
    POSITIVE LOGITS
    MessageOf
    0.71
     AssemblyCulture
    0.71
    uxxxx
    0.68
    TagMode
    0.66
    GeneratedCode
    0.65
    elemField
    0.64
    windowFixed
    0.63
    featureID
    0.62
    @[+][
    0.61
    ///</
    0.60
    Activations Density 0.013%

    No Known Activations