© 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. 1-CLT-HP
    7. 12248
    Prev
    Next
    INDEX
    Explanations

    official statements

    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
     spokesperson
    -2.22
     spokesman
    -2.14
     Spokes
    -1.95
     spokeswoman
    -1.92
     spokespersons
    -1.48
     spokes
    -1.45
    Spo
    -1.15
     portavoz
    -0.99
    spo
    -0.93
     representative
    -0.82
    POSITIVE LOGITS
     garantiza
    0.57
     OFDb
    0.48
     for
    0.45
     umane
    0.44
    iness
    0.44
     manquer
    0.43
     umana
    0.42
    anship
    0.42
    ädie
    0.42
    nél
    0.41
    Activations Density 0.005%

    No Known Activations