© 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. 1220
    Prev
    Next
    INDEX
    Explanations

    correctness/validity

    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
    +#+#
    -0.83
     resourceCulture
    -0.71
     disambiguazione
    -0.65
    rungsseite
    -0.64
    DockStyle
    -0.63
    SequentialGroup
    -0.62
    Démographie
    -0.60
    CppCodeGen
    -0.57
    EventQueue
    -0.56
    ConstraintMaker
    -0.56
    POSITIVE LOGITS
     noqa
    0.57
    typeparam
    0.52
    仿
    0.47
     taps
    0.46
    stination
    0.45
    extAlignment
    0.45
     onOptions
    0.45
     ovation
    0.44
    InitVars
    0.44
    lah
    0.43
    Activations Density 0.068%

    No Known Activations