© 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. 12281
    Prev
    Next
    INDEX
    Explanations

    information related to lists of notable figures or categories, particularly in the context of historical or cultural contributions

    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
    دانشنامهٔ
    -0.69
    ]){
    -0.66
    __))
    -0.59
     AssemblyTitle
    -0.57
    XmlType
    -0.56
    '],
    -0.55
    "],
    -0.55
    vician
    -0.55
    '){
    -0.54
    '))
    -0.54
    POSITIVE LOGITS
    <?,
    0.60
    glEnd
    0.52
    ровано
    0.51
    poň
    0.50
    phro
    0.49
    JvmStatic
    0.48
     Grady
    0.48
    Table
    0.48
    Skocz
    0.48
    LayoutPanel
    0.47
    Activations Density 0.260%

    No Known Activations