© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9287
    Prev
    Next
    INDEX
    Explanations

    share

    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
    CloseOperation
    -0.93
    makeConstraints
    -0.88
    Билгалдахарш
    -0.79
    ⓧ
    -0.76
    IonicModule
    -0.69
    таратура
    -0.69
    Datuak
    -0.68
     AttributeSet
    -0.67
     שוליים
    -0.66
     للمعارف
    -0.65
    POSITIVE LOGITS
     grievances
    0.53
    aderie
    0.48
    phrine
    0.42
     associ
    0.41
    litos
    0.41
    $")
    0.40
     popcorn
    0.39
     grievance
    0.39
    ()")
    0.39
    Amicalement
    0.38
    Activations Density 0.007%

    No Known Activations