© 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. 20-CLT-HP
    7. 74738
    Prev
    Next
    INDEX
    Explanations

    Informal writing

    np_max-act-logits · 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
    oredCriteria
    -0.74
    rungsseite
    -0.65
    IntoConstraints
    -0.64
    省市镇
    -0.63
     VizieR
    -0.62
    ########.
    -0.54
    ंदीखरीदारी
    -0.53
    
    -0.52
     Bioaccumulative
    -0.52
     Dummies
    -0.52
    POSITIVE LOGITS
     pivot
    0.61
    pivot
    0.58
     all
    0.57
     over
    0.52
    annica
    0.48
     pivo
    0.47
    all
    0.47
    ounted
    0.46
    <h6>
    0.46
     outstanding
    0.45
    Activations Density 0.000%

    No Known Activations