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. 10990
    Prev
    Next
    INDEX
    Explanations

    oid

    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
    mold
    -0.54
    cath
    -0.50
     mold
    -0.47
    gor
    -0.47
     aapt
    -0.45
    #+#
    -0.45
     πά
    -0.45
    hydro
    -0.44
    ArgsConstructor
    -0.44
    signatures
    -0.44
    POSITIVE LOGITS
    Personensuche
    0.69
    Autoritní
    0.65
    EndContext
    0.63
     jadx
    0.63
    y
    0.61
    WebElementEntity
    0.60
     pinulongan
    0.57
    ed
    0.57
     depositphotos
    0.56
     незавершена
    0.56
    Activations Density 0.012%

    No Known Activations