© 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. 5-CLT-HP
    7. 91326
    Prev
    Next
    INDEX
    Explanations

    article descriptions

    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
    yntaxException
    -0.86
     pageContext
    -0.66
    itinéraire
    -0.58
     socialize
    -0.56
     bankers
    -0.56
     astronomy
    -0.56
    ᅠ
    -0.56
    upuncture
    -0.56
     Glanz
    -0.56
     artwork
    -0.55
    POSITIVE LOGITS
     regulares
    0.45
    migrationBuilder
    0.44
     ***!
    0.43
    guém
    0.42
     QName
    0.42
     panggilan
    0.42
     majeurs
    0.41
    SuppressMessage
    0.40
     henkilö
    0.40
    первых
    0.40
    Activations Density 0.008%

    No Known Activations