© 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. 71783
    Prev
    Next
    INDEX
    Explanations

    Foreign 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
    躇
    -0.63
    Parcelize
    -0.58
    MemoryWarning
    -0.52
     createContext
    -0.48
    Hochspringen
    -0.46
    Clik
    -0.46
    enumi
    -0.46
     MediatR
    -0.46
    ScopeManager
    -0.45
     IMDG
    -0.45
    POSITIVE LOGITS
    хьтан
    0.62
     كومونز
    0.52
    TypedDataSet
    0.51
    Salta
    0.51
    ACC
    0.50
    pektrum
    0.50
    ZIE
    0.49
     незавершена
    0.48
    Demografie
    0.47
    biega
    0.46
    Activations Density 0.000%

    No Known Activations