© 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. 39957
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    ikum
    -1.95
     Obispo
    -0.55
    prototype
    -0.50
    >*/
    -0.50
     doublet
    -0.48
     neto
    -0.47
     Clipper
    -0.47
     ruote
    -0.47
     Colton
    -0.46
    rawDesc
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    0.83
     surla
    0.81
    esez
    0.73
    mbggenerated
    0.67
    AutoScaleMode
    0.67
    isContained
    0.65
     propOrder
    0.65
    HasBeenSet
    0.62
     للاسماء
    0.60
    GenerationType
    0.60
    Activations Density 1.162%

    No Known Activations