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. 10979
    Prev
    Next
    INDEX
    Explanations

    right parentheses

    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
    ,
    -1.39
    -
    -1.30
    .
    -1.16
    :
    -1.05
    /
    -1.02
    (
    -0.98
    "
    -0.98
    '
    -0.96
    ;
    -0.94
    )
    -0.92
    POSITIVE LOGITS
    ⓧ
    0.70
     lèvres
    0.60
     ferons
    0.59
     autorytatywna
    0.57
     excès
    0.57
     vœux
    0.56
     cérami
    0.56
    Personendaten
    0.55
    AndroidJUnit
    0.55
     soucis
    0.54
    Activations Density 0.024%

    No Known Activations