© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75253
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous topics

    np_max-act-logits · 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
     refroid
    -0.59
     popoli
    -0.58
     politiet
    -0.54
     noires
    -0.53
     genoux
    -0.50
     scolaires
    -0.49
     carrés
    -0.49
     variés
    -0.49
     vicenda
    -0.49
     vieill
    -0.48
    POSITIVE LOGITS
    SequentialGroup
    0.73
     inf
    0.65
     dàng
    0.63
    XtraEditors
    0.62
     kept
    0.61
    InjectAttribute
    0.60
    XmlAccessType
    0.60
     indoor
    0.60
     erop
    0.59
    yarnpkg
    0.59
    Activations Density 0.000%

    No Known Activations