© 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. 1-CLT-HP
    7. 437
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    GEBURTS
    -0.76
     InputDecoration
    -0.75
    DotNetBar
    -0.74
     ویکی‌پدیای
    -0.72
     surla
    -0.71
    ########.
    -0.68
    __":
    -0.68
    saraba
    -0.66
    pexpr
    -0.64
     noDo
    -0.63
    POSITIVE LOGITS
    不起
    0.55
     насељу
    0.44
    limin
    0.42
    Investigations
    0.41
     Expanded
    0.41
    ForRow
    0.40
    帖最后由
    0.40
    Espèce
    0.40
    grove
    0.38
     Rep
    0.38
    Activations Density 0.049%

    No Known Activations