© 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. 91056
    Prev
    Next
    INDEX
    Explanations

    Notifications/reports

    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
     ſtate
    -0.75
     faſt
    -0.72
     Remarks
    -0.71
     ſta
    -0.70
     myſelf
    -0.69
     Diſ
    -0.66
     ſtand
    -0.66
     Houſe
    -0.66
     fhort
    -0.66
     poffible
    -0.65
    POSITIVE LOGITS
     Савезне
    0.83
     ModelExpression
    0.79
    expandindo
    0.75
    تقاوى
    0.71
    httphttps
    0.69
    :✨
    0.68
    Enllaces
    0.68
    fromnode
    0.68
    protoimpl
    0.67
    WriteAttribute
    0.66
    Activations Density 0.773%

    No Known Activations