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. 73860
    Prev
    Next
    INDEX
    Explanations

    Domestic

    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
    <?
    -0.54
     prêts
    -0.44
     vérit
    -0.42
    com
    -0.42
    usercontent
    -0.42
     investissements
    -0.42
    ⁢
    -0.41
     enfans
    -0.40
    bör
    -0.40
     lignes
    -0.40
    POSITIVE LOGITS
    Билгалдахарш
    0.80
    parsedMessage
    0.73
     witcher
    0.72
     GAC
    0.71
     LEC
    0.71
     GSC
    0.69
    RuleContext
    0.69
     SSC
    0.69
    yntaxException
    0.68
     GLE
    0.67
    Activations Density 0.000%

    No Known Activations