© 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. 20-CLT-HP
    7. 73064
    Prev
    Next
    INDEX
    Explanations

    Text from longer texts

    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
    Personensuche
    -1.01
     المعيارى
    -0.83
    InjectAttribute
    -0.80
     /\.
    -0.69
    featureID
    -0.66
    audiovisuel
    -0.65
    تقاوى
    -0.64
    帖最后由
    -0.64
    存于互联网档案馆
    -0.63
    LookAnd
    -0.63
    POSITIVE LOGITS
    blers
    0.52
    bler
    0.48
     سكان
    0.45
    gable
    0.45
     Kan
    0.43
    gence
    0.42
    ुर
    0.42
    ued
    0.42
    gal
    0.42
     count
    0.41
    Activations Density 0.000%

    No Known Activations