© 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. 39870
    Prev
    Next
    INDEX
    Explanations

    technical/scientific writing

    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
    excellents
    -0.54
     Audiodateien
    -0.54
     prisonniers
    -0.54
     colère
    -0.52
     meines
    -0.50
     fieltro
    -0.49
    Bibliograf
    -0.49
     démocr
    -0.47
     blessés
    -0.47
    jatel
    -0.47
    POSITIVE LOGITS
    WriteAttribute
    0.72
    ArgsConstructor
    0.66
     nonatomic
    0.66
    makeText
    0.63
     BoxFit
    0.61
    setViewportView
    0.61
    IsMutable
    0.59
    xmlWriter
    0.59
    keyColumn
    0.57
    NegativeButton
    0.56
    Activations Density 0.119%

    No Known Activations