© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4580
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
     ModelExpression
    -0.63
    Autoritní
    -0.60
    KommentareTeilen
    -0.59
    ]++;
    -0.56
     незавершена
    -0.56
    ]='\
    -0.54
    CompilerServices
    -0.54
    الدراسه
    -0.53
    ↑↑
    -0.53
    amment
    -0.52
    POSITIVE LOGITS
     onPostExecute
    0.54
    '
    0.53
     word
    0.53
    Jereo
    0.52
    ’
    0.49
     keys
    0.45
     appears
    0.44
     Charlemagne
    0.43
     bearer
    0.43
     KeyError
    0.43
    Activations Density 0.001%

    No Known Activations