© 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. 1960
    Prev
    Next
    INDEX
    Explanations

    code and writing excerpts

    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
    Lähteet
    -0.48
     $\%
    -0.47
     referrerpolicy
    -0.47
    وبه
    -0.45
     Amore
    -0.45
    fml
    -0.44
    addPreferredGap
    -0.44
     sekali
    -0.43
    伝
    -0.43
    ister
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
    providedIn
    0.71
    DebuggerNonUser
    0.67
    SharedDtor
    0.66
    TypedDataSet
    0.65
    hyrchwyd
    0.63
    adaptiveStyles
    0.60
    Personensuche
    0.59
    styleable
    0.57
    addCriterion
    0.57
    Activations Density 0.005%

    No Known Activations