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. 5-CLT-HP
    4. 95614
    Prev
    Next
    INDEX
    Explanations

    that

    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
    balleur
    -0.78
    цездатний
    -0.77
    랬
    -0.71
    Tikang
    -0.70
    ustimmung
    -0.69
    osphere
    -0.68
    iqué
    -0.67
    matum
    -0.67
    labus
    -0.66
    fficacy
    -0.66
    POSITIVE LOGITS
    <bos>
    0.47
     conseguenza
    0.43
     préoccup
    0.41
    zuf
    0.40
     capables
    0.38
    Билгалдахарш
    0.35
     شک
    0.34
     waardoor
    0.34
    ież
    0.33
    from
    0.33
    Activations Density 0.003%

    No Known Activations