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. 20-CLT-HP
    4. 74344
    Prev
    Next
    INDEX
    Explanations

    Proper nouns

    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
    gaged
    -0.38
    Jeografia
    -0.36
    cinogenicity
    -0.35
    __*/
    -0.34
     Diakses
    -0.34
    ยาก
    -0.32
    ,‎
    -0.31
    parsedMessage
    -0.29
    onym
    -0.29
    üyada
    -0.29
    POSITIVE LOGITS
    NOPQRST
    0.82
     Records
    0.79
     Syndrome
    0.76
     Network
    0.75
     Holdings
    0.75
     Resort
    0.74
     Corporation
    0.74
     Airlines
    0.73
     fumée
    0.73
     Disorder
    0.73
    Activations Density 0.002%

    No Known Activations