© 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. 4-CLT-HP
    7. 523
    Prev
    Next
    INDEX
    Explanations

    non-digestible compounds

    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
    PreferredItem
    -0.58
    fortawesome
    -0.50
    InputLabel
    -0.48
    vosť
    -0.48
    UserScript
    -0.48
    PARATUS
    -0.46
    ISPR
    -0.44
    EDEFAULT
    -0.44
     FRP
    -0.44
    fieldLabel
    -0.42
    POSITIVE LOGITS
    tible
    0.64
    veland
    0.61
    interopRequire
    0.60
    cend
    0.58
    WEBPACK
    0.57
     الاطلاع
    0.57
    ajah
    0.55
    tanleria
    0.54
    UAL
    0.53
    ted
    0.52
    Activations Density 0.002%

    No Known Activations