© 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. 44148
    Prev
    Next
    INDEX
    Explanations

    technical

    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
     Truss
    -0.68
    WebVitals
    -0.66
    lebo
    -0.65
    #+#
    -0.65
     Cáceres
    -0.64
    luence
    -0.63
     abandon
    -0.61
    elemField
    -0.61
     deserts
    -0.61
    ंदीखरीदारी
    -0.60
    POSITIVE LOGITS
    lin
    0.50
    way
    0.49
    Hope
    0.48
    vante
    0.48
    [toxicity=0]
    0.48
     Hope
    0.47
    altor
    0.47
     of
    0.47
    ger
    0.47
    line
    0.46
    Activations Density 0.317%

    No Known Activations