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. 0-CLT-HP
    4. 39461
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     tess
    -0.77
    rez
    -0.67
    rec
    -0.66
    UnsafeEnabled
    -0.62
    ujan
    -0.58
    TintMode
    -0.53
    plen
    -0.51
    ged
    -0.50
    AutoScaleMode
    -0.49
    migrationBuilder
    -0.48
    POSITIVE LOGITS
     chariots
    0.74
    couvrez
    0.64
    XtraEditors
    0.62
    +#+#
    0.59
    الإنجليزية
    0.58
    icycle
    0.57
    KommentareTeilen
    0.55
    Clik
    0.54
     Amat
    0.54
    ClientRect
    0.54
    Activations Density 0.182%

    No Known Activations