© 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. 0-CLT-HP
    7. 39824
    Prev
    Next
    INDEX
    Explanations

    external sources/references

    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
    parsedMessage
    -1.04
    kháu
    -1.03
    IsMutable
    -1.03
     SafeMath
    -1.00
    مقاله
    -0.97
    帖最后由
    -0.97
    Hauptartikel
    -0.95
     AssemblyTitle
    -0.95
     snippetHide
    -0.94
     Roskov
    -0.94
    POSITIVE LOGITS
    The
    0.84
    .
    0.78
    2
    0.77
    1
    0.72
    A
    0.71
    ↵↵
    0.69
    5
    0.68
    E
    0.66
    3
    0.66
    4
    0.66
    Activations Density 0.223%

    No Known Activations