© 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. 18-RES-MATRYOSHKA-DC
    7. 729
    Prev
    Next
    INDEX
    Explanations

    lines of code or data with identifying characters and numbers.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    <bos>
    -1.05
    Sucesor
    -0.77
    contentLoaded
    -0.76
    exitRule
    -0.56
    Traducción
    -0.55
     "<?
    -0.54
    fillType
    -0.54
    省市镇
    -0.54
     '<?
    -0.53
    findpost
    -0.52
    POSITIVE LOGITS
    DoubleQuotes
    0.63
    RenderAtEndOf
    0.61
    getDoctrine
    0.59
     др
    0.58
    VersionUID
    0.56
    appé
    0.56
    chengladbach
    0.56
    ArgsConstructor
    0.54
    lectricité
    0.53
    spesies
    0.53
    Activations Density 0.613%

    No Known Activations