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. 74348
    Prev
    Next
    INDEX
    Explanations

    mathematical/scientific notation

    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
     faſt
    -0.71
     pleaſure
    -0.71
     purpoſe
    -0.66
     Theſe
    -0.65
     Monfieur
    -0.63
     poffe
    -0.61
     houſe
    -0.60
     Trades
    -0.60
     Efq
    -0.60
     trades
    -0.59
    POSITIVE LOGITS
     ويكيميديا
    0.53
    ⓧ
    0.51
    Rüyada
    0.46
     aurez
    0.45
     pratiquer
    0.45
    tsin
    0.45
     extérieures
    0.44
     "));
    0.44
    cusión
    0.44
    rungsseite
    0.44
    Activations Density 0.003%

    No Known Activations