© 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. 91107
    Prev
    Next
    INDEX
    Explanations

    pathogenesis

    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
     NSCoder
    -0.79
     utafitiHapana
    -0.79
     femininas
    -0.79
    orari
    -0.77
     lèvres
    -0.77
     educativas
    -0.75
     navires
    -0.75
     tartalomajánló
    -0.74
     malades
    -0.73
    gypti
    -0.73
    POSITIVE LOGITS
    otas
    0.52
     C
    0.47
    otin
    0.45
     Fal
    0.44
     items
    0.43
    imia
    0.43
     ha
    0.42
     B
    0.42
     Á
    0.41
    тен
    0.41
    Activations Density 0.305%

    No Known Activations