© 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. 45129
    Prev
    Next
    INDEX
    Explanations

    code/mathematical language

    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
    scriptcase
    -0.56
     ne
    -0.52
     zá
    -0.50
     par
    -0.47
    сня
    -0.47
    endphp
    -0.47
     convirtió
    -0.45
    ...
    -0.45
    keit
    -0.44
     bocas
    -0.43
    POSITIVE LOGITS
    exitRule
    0.72
    onAttach
    0.68
    BibitemShut
    0.65
     Hsi
    0.62
    xFFFFFFFF
    0.61
     vPvB
    0.61
     feuille
    0.60
    vereign
    0.60
     كومونز
    0.59
    '")
    0.59
    Activations Density 0.115%

    No Known Activations