© 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. 1-CLT-HP
    7. 9886
    Prev
    Next
    INDEX
    Explanations

    Descriptive text

    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
     candle
    -0.97
     candles
    -0.97
     Candles
    -0.95
     Candle
    -0.85
    Candle
    -0.83
    Candles
    -0.82
    candles
    -0.81
    candle
    -0.79
     bougies
    -0.68
     correctes
    -0.66
    POSITIVE LOGITS
    ")));
    0.55
    hip
    0.53
    ücks
    0.50
    ""}
    0.49
     nahilalakip
    0.49
     ")");
    0.49
    )));
    0.49
     "}";
    0.48
     "..\..\
    0.47
     Ferdinand
    0.47
    Activations Density 0.014%

    No Known Activations