© 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. 5-CLT-HP
    7. 5925
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    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
     brome
    -0.54
     consultato
    -0.54
     recommandée
    -0.52
    StreetMap
    -0.49
    DoubleQuotes
    -0.47
     שוליים
    -0.47
     Accesat
    -0.47
     twins
    -0.45
    Reducers
    -0.45
    acağına
    -0.45
    POSITIVE LOGITS
    хьтан
    0.72
     pinulongan
    0.71
     CURIAM
    0.62
    最快更新
    0.61
     المعيارى
    0.56
    contentLoaded
    0.55
    issão
    0.53
    ⓧ
    0.53
    assies
    0.52
    onAttach
    0.52
    Activations Density 0.002%

    No Known Activations