© 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. 1-CLT-HP
    7. 14552
    Prev
    Next
    INDEX
    Explanations

    variables

    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
     CreateTagHelper
    -0.88
    :✨
    -0.81
    KommentareTeilen
    -0.74
     חיצוניים
    -0.74
    ouncement
    -0.69
    igshid
    -0.69
     BoxFit
    -0.69
    ERVIEW
    -0.69
    adaptiveStyles
    -0.68
     للمعارف
    -0.67
    POSITIVE LOGITS
    ’
    0.56
    '
    0.56
    aarrggbb
    0.49
    (
    0.42
     seu
    0.41
    \
    0.39
     faccia
    0.38
    js
    0.38
    Parameteri
    0.38
    DebuggerNonUser
    0.38
    Activations Density 0.040%

    No Known Activations