© 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. 3-RES-MATRYOSHKA-DC
    7. 1984
    Prev
    Next
    INDEX
    Explanations

    instances of cutting, slicing, or incising

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Попис
    -0.74
    ThroughAttribute
    -0.71
    Бахар
    -0.70
    DockStyle
    -0.69
    brates
    -0.68
     Senhora
    -0.68
     Nanda
    -0.67
     typelib
    -0.66
    Dh
    -0.63
    rowid
    -0.63
    POSITIVE LOGITS
     cut
    3.47
     Cut
    3.25
     cuts
    3.23
    cut
    3.19
    Cut
    3.11
     CUT
    3.05
     Cuts
    2.94
     cutting
    2.92
    CUT
    2.92
    cuts
    2.91
    Activations Density 0.601%

    No Known Activations