© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93235
    Prev
    Next
    INDEX
    Explanations

    XHTML

    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
     XHTML
    -1.21
    poe
    -0.84
    PerformLayout
    -0.78
    extAlignment
    -0.72
    зулта
    -0.69
     فريبيس
    -0.63
    رشف
    -0.59
    illus
    -0.57
    KURZBESCHREIBUNG
    -0.57
    LookAnd
    -0.57
    POSITIVE LOGITS
     Saddle
    0.51
    omia
    0.47
    PRODUCTION
    0.47
    sidemargin
    0.47
    terse
    0.46
    Producción
    0.45
    phoria
    0.44
     successful
    0.43
    สิน
    0.43
    konferenz
    0.43
    Activations Density 0.100%

    No Known Activations