© 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. 91675
    Prev
    Next
    INDEX
    Explanations

    software documentation excerpts

    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
    NameInMap
    -0.87
    contentLoaded
    -0.84
    QMetaType
    -0.81
    存于互联网档案馆
    -0.80
    ArgsConstructor
    -0.80
    Personensuche
    -0.79
     виправивши
    -0.78
     AspNetCore
    -0.78
    PerformLayout
    -0.77
    évaluateur
    -0.77
    POSITIVE LOGITS
    ndon
    0.41
    kus
    0.39
    struct
    0.39
    acterium
    0.38
     ill
    0.38
    estinian
    0.37
     maß
    0.37
    redhat
    0.37
    XMLSchema
    0.36
     laik
    0.36
    Activations Density 0.022%

    No Known Activations