Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12908
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    LEncoder
    -0.73
    Билгалдахарш
    -0.73
    enderror
    -0.72
    ParallelGroup
    -0.72
    Manbalar
    -0.70
     GenerationType
    -0.69
     >=",
    -0.67
    TargetException
    -0.63
    writeField
    -0.63
    webElementGuid
    -0.62
    POSITIVE LOGITS
     that
    0.77
     there
    0.58
     "[
    0.58
    edale
    0.52
     it
    0.52
     Serializable
    0.49
     Ceram
    0.49
     '<?
    0.48
    that
    0.47
     Integr
    0.46
    Activations Density 0.012%

    No Known Activations