© 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. 28491
    Prev
    Next
    INDEX
    Explanations

    references to documentation URLs

    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
    GeneratedMessage
    -0.73
    pexpr
    -0.73
    
    -0.69
    RectangleBorder
    -0.65
    aise
    -0.64
    ."],
    -0.64
    Spoljašnje
    -0.62
     clearColor
    -0.62
     pngtree
    -0.60
    MigrationBuilder
    -0.60
    POSITIVE LOGITS
    docs
    1.02
     GenerationType
    0.81
     docs
    0.73
    GenerationType
    0.70
    Docs
    0.69
    ríguez
    0.66
    |:
    0.63
    igshid
    0.63
     Docs
    0.63
    Firestore
    0.61
    Activations Density 0.003%

    No Known Activations