© 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. 20-CLT-HP
    7. 74512
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · 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
    textTheme
    -0.62
    wieś
    -0.59
    createCanvas
    -0.54
    Спољашње
    -0.52
     Winaray
    -0.52
     ReSharper
    -0.51
    ORCID
    -0.51
    GUILayout
    -0.50
    tés
    -0.49
    Personensuche
    -0.48
    POSITIVE LOGITS
    webElementXpaths
    0.60
    avax
    0.52
    CommandText
    0.51
     conjug
    0.49
    balleur
    0.49
    fieldId
    0.48
    aarrggbb
    0.48
     setObject
    0.48
    />";
    0.48
     heure
    0.48
    Activations Density 0.002%

    No Known Activations