© 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. 72868
    Prev
    Next
    INDEX
    Explanations

    minute

    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
    tagHelperRunner
    -1.03
     للاسماء
    -0.88
    UnusedPrivate
    -0.81
    IUrlHelper
    -0.79
     Rest
    -0.77
    ConstraintMaker
    -0.76
    SequentialGroup
    -0.76
     صوتيه
    -0.75
     مرئيه
    -0.72
    лтемелер
    -0.71
    POSITIVE LOGITS
     complete
    0.47
    Trusted
    0.41
    ISupport
    0.41
    complete
    0.38
     absolute
    0.36
     perfect
    0.35
    Scooby
    0.35
     true
    0.34
     periods
    0.33
     абсолю
    0.33
    Activations Density 0.000%

    No Known Activations