© 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. 20-CLT-HP
    7. 71822
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
     commerciali
    -0.50
    fp
    -0.45
     femmin
    -0.43
     FBref
    -0.42
    Rhestr
    -0.42
    FP
    -0.40
     zelo
    -0.40
     geométrico
    -0.40
     fréquent
    -0.40
    endor
    -0.39
    POSITIVE LOGITS
    GEBURTSDATUM
    0.71
    XmlAccessType
    0.66
     bezeichneter
    0.65
    клопе
    0.65
     noDo
    0.61
    parsedMessage
    0.61
    BackStack
    0.59
    اریخ
    0.59
    ScopeManager
    0.58
    tase
    0.58
    Activations Density 0.003%

    No Known Activations