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. 1-CLT-HP
    4. 12625
    Prev
    Next
    INDEX
    Explanations

    physics/engineering

    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
     met
    -0.42
    fle
    -0.42
     paio
    -0.40
    ご
    -0.40
     क्ष
    -0.40
    Fitted
    -0.39
    lacement
    -0.39
     fit
    -0.38
    '
    -0.38
    Recovered
    -0.38
    POSITIVE LOGITS
    extAlignment
    0.85
    __(/*!
    0.80
     kasarigan
    0.80
    RenderAtEndOf
    0.79
     محفوظة
    0.78
     مُعرِّف
    0.77
     myſelf
    0.76
     Majefty
    0.74
    endphp
    0.73
     CURLOPT
    0.73
    Activations Density 0.946%

    No Known Activations