© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 806
    Prev
    Next
    INDEX
    Explanations

    formal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lump
    -1.01
    lump
    -0.91
     Lump
    -0.86
     lumps
    -0.79
    UnknownFields
    -0.72
     LUMP
    -0.69
     chi̍t
    -0.64
    aarrggbb
    -0.62
     ModelExpression
    -0.62
    amation
    -0.60
    POSITIVE LOGITS
     insuffisamment
    0.50
    shadowOpacity
    0.43
    board
    0.43
    //};
    0.42
     vitale
    0.41
    ed
    0.41
     lê
    0.39
    ilever
    0.38
    ťou
    0.38
     réalisation
    0.37
    Activations Density 0.015%

    No Known Activations