Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3895
    Prev
    Next
    INDEX
    Explanations

    Subject

    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
    lysis
    -0.42
     gne
    -0.39
    rari
    -0.39
    itively
    -0.39
    jinal
    -0.39
    ully
    -0.38
     Keep
    -0.38
    shadowRadius
    -0.37
    undheit
    -0.37
    rean
    -0.37
    POSITIVE LOGITS
    GEBURTSDATUM
    0.77
    Itoa
    0.66
     réglage
    0.61
     ausged
    0.59
    Autoritní
    0.56
    binaan
    0.55
    MigrationBuilder
    0.54
     szóci
    0.54
    Gambas
    0.54
     TextAppearance
    0.53
    Activations Density 0.009%

    No Known Activations