© 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. 12192
    Prev
    Next
    INDEX
    Explanations

    JP

    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
     Brent
    -0.53
     såsom
    -0.51
     Honey
    -0.51
    ulitan
    -0.48
    Brent
    -0.47
    Tow
    -0.47
    momile
    -0.46
     JP
    -0.45
    Burt
    -0.44
     sent
    -0.44
    POSITIVE LOGITS
     समीक्षाएं
    0.64
    HasColumnType
    0.61
     abſ
    0.57
    UnitTesting
    0.57
    .*")]
    0.57
     Normdatei
    0.54
    ----</
    0.54
     pediatrician
    0.54
    CppMethod
    0.54
     neceſſ
    0.54
    Activations Density 0.225%

    No Known Activations