© 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. 44001
    Prev
    Next
    INDEX
    Explanations

    sper

    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
    
    -0.74
    endphp
    -0.72
    riwal
    -0.68
     âgées
    -0.62
     housework
    -0.61
     Référence
    -0.61
     Bobo
    -0.61
     سكانية
    -0.60
    timacy
    -0.60
     Bantu
    -0.59
    POSITIVE LOGITS
    principalTable
    0.53
     Evans
    0.49
     in
    0.47
    AnchorStyles
    0.47
    OutOfRange
    0.47
    auc
    0.46
    jos
    0.45
    istisches
    0.45
    Soorten
    0.45
    queryset
    0.43
    Activations Density 0.098%

    No Known Activations