© 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. 17600
    Prev
    Next
    INDEX
    Explanations

    statistical significance and effects in scientific studies

    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
    AddHtmlAttribute
    -0.55
    ISupport
    -0.50
     zam
    -0.48
    Nel
    -0.47
    glDelete
    -0.46
    vest
    -0.45
    جغرافيا
    -0.45
     发表于
    -0.44
    moveToFirst
    -0.43
     Signing
    -0.42
    POSITIVE LOGITS
    <()>
    0.84
    phosa
    0.69
     disponibilités
    0.68
     createContext
    0.67
    Kaynakça
    0.66
    //
    0.66
    PhysRev
    0.66
     ModelRenderer
    0.66
     ब्रेकडाउन
    0.65
    imageshack
    0.65
    Activations Density 0.007%

    No Known Activations