© 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. 39816
    Prev
    Next
    INDEX
    Explanations

    ally

    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
    column
    -1.08
     column
    -1.07
     columns
    -0.97
    columns
    -0.89
    Column
    -0.88
    pillar
    -0.86
     columnas
    -0.85
    Columns
    -0.82
     colonnes
    -0.82
     Column
    -0.77
    POSITIVE LOGITS
    EDEFAULT
    0.69
    __*/
    0.66
     ExecuteAsync
    0.60
     Elles
    0.59
    تقاوى
    0.58
     closest
    0.57
    IsContent
    0.56
     she
    0.56
     cherchés
    0.56
    tagHelperRunner
    0.55
    Activations Density 0.044%

    No Known Activations