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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1208
    Prev
    Next
    INDEX
    Explanations

    as

    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
     genoux
    -0.69
    "]));
    -0.67
     épaules
    -0.63
     décennies
    -0.60
     lèvres
    -0.58
     œufs
    -0.57
    ]),
    -0.56
    SerializedName
    -0.54
    quelize
    -0.54
    ()");
    -0.54
    POSITIVE LOGITS
     replacements
    0.76
     substitutes
    0.71
     alternatives
    0.70
     targets
    0.69
     options
    0.67
     gifts
    0.66
     indicators
    0.66
     components
    0.65
     examples
    0.65
     solutions
    0.65
    Activations Density 0.032%

    No Known Activations