© 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. 25729
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and relationships involving functions and variables

    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
     rye
    -0.59
     addItem
    -0.57
    Vorlage
    -0.57
    cshtml
    -0.54
    ++];
    -0.54
    velas
    -0.53
     &___
    -0.52
    IntoConstraints
    -0.52
     mohair
    -0.52
    Географи
    -0.52
    POSITIVE LOGITS
    новниш
    0.69
    ScopeManager
    0.54
    RenderAtEndOf
    0.54
    ということです
    0.50
    tr
    0.49
    te
    0.46
    ってこと
    0.46
     `
    0.45
    шеб
    0.45
    ByPrimaryKey
    0.44
    Activations Density 0.209%

    No Known Activations