© 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. 76364
    Prev
    Next
    INDEX
    Explanations

    code or science

    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
     Socialista
    -0.67
    +#+
    -0.60
     pédagogique
    -0.60
     Nacionales
    -0.59
     sanitaires
    -0.59
     Wikimedijinoj
    -0.58
     blancs
    -0.57
    .*")]
    -0.57
    ńczy
    -0.56
     فريبيس
    -0.56
    POSITIVE LOGITS
     res
    0.58
     nakalista
    0.57
    res
    0.50
    EndContext
    0.50
    SQLiteDatabase
    0.47
    itable
    0.45
     GenerationType
    0.43
     Ti
    0.43
     Res
    0.42
    BagLayout
    0.42
    Activations Density 0.001%

    No Known Activations