© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92058
    Prev
    Next
    INDEX
    Explanations

    independent

    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
     of
    -0.73
    ymce
    -0.54
     tiennent
    -0.49
    .*")]
    -0.49
    providedIn
    -0.49
     fotografico
    -0.48
    RelativeTo
    -0.48
     conformément
    -0.47
     manquer
    -0.47
     trasparente
    -0.47
    POSITIVE LOGITS
     existence
    0.91
    createCanvas
    0.62
     الرياضيه
    0.58
     operation
    0.58
    existence
    0.57
     exist
    0.54
     action
    0.54
     investigation
    0.54
    cèse
    0.53
     creation
    0.52
    Activations Density 0.002%

    No Known Activations