© 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. 5-CLT-HP
    7. 2098
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
    CppMethod
    -0.76
    featureID
    -0.75
     disambiguazione
    -0.71
    ArrowToggle
    -0.70
     beginnetje
    -0.67
    Personensuche
    -0.63
    "]];
    -0.61
    TypedDataSet
    -0.60
    //
    -0.60
    RTSC
    -0.60
    POSITIVE LOGITS
     sauter
    0.52
    cinogen
    0.50
     fail
    0.45
     turn
    0.44
    setViewport
    0.42
     mediodía
    0.42
     världen
    0.41
     solitario
    0.41
     crescita
    0.40
     reach
    0.39
    Activations Density 0.021%

    No Known Activations