© 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. 1-CLT-HP
    7. 487
    Prev
    Next
    INDEX
    Explanations

    creative endeavors

    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
     الحره
    -0.81
     Shakspeare
    -0.77
    StoryboardSegue
    -0.75
     Cæsar
    -0.73
    extAlignment
    -0.72
     дописавши
    -0.72
     Monfieur
    -0.70
     himſelf
    -0.69
     للاسماء
    -0.68
     الرياضيه
    -0.68
    POSITIVE LOGITS
     án
    0.53
    vál
    0.45
    +:+
    0.45
    zaamheid
    0.45
     fiel
    0.44
     Pump
    0.44
    lah
    0.43
    lete
    0.43
     Works
    0.42
    Ladder
    0.42
    Activations Density 0.047%

    No Known Activations