© 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. 1-CLT-HP
    7. 9578
    Prev
    Next
    INDEX
    Explanations

    inos

    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
     Walkover
    -0.62
    ⓘ
    -0.54
    Portail
    -0.54
     상세
    -0.49
    [
    -0.48
     اطلع
    -0.47
    stdc
    -0.47
     cherchés
    -0.46
    >//
    -0.46
     il
    -0.44
    POSITIVE LOGITS
     Jefus
    0.84
     raiſ
    0.82
    ſelf
    0.82
     ſhe
    0.82
     ſtand
    0.81
     becauſe
    0.79
     Anſ
    0.79
     itſelf
    0.79
     themſelves
    0.78
     ſta
    0.78
    Activations Density 0.033%

    No Known Activations