© 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. 76580
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    +#+#
    -0.90
    migrationBuilder
    -0.63
    homonymie
    -0.60
    XmlAccessType
    -0.59
    __(/*!
    -0.58
    TacToe
    -0.56
     uffic
    -0.56
     MotionEvent
    -0.55
    TestingModule
    -0.54
    Xna
    -0.54
    POSITIVE LOGITS
    ziasztok
    0.52
     NDEBUG
    0.51
     garden
    0.49
    setVerticalGroup
    0.47
     Garden
    0.46
    Jîn
    0.46
    setLevel
    0.45
     GARDEN
    0.45
    chers
    0.44
    Adults
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.