© 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. 4-CLT-HP
    7. 486
    Prev
    Next
    INDEX
    Explanations

    lists and separators

    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
     GenerationType
    -0.63
    Ծանոթ
    -0.62
    StoryboardSegue
    -0.61
    معلومات
    -0.60
    Spoljašnje
    -0.58
    zeptember
    -0.58
    Revenir
    -0.58
     zubehör
    -0.57
     is
    -0.57
     esfuer
    -0.56
    POSITIVE LOGITS
    umina
    0.44
    acabana
    0.42
    protoimpl
    0.42
    ddr
    0.41
    __/
    0.40
    Drink
    0.39
    andolo
    0.39
    styleable
    0.39
     seize
    0.39
     Suez
    0.39
    Activations Density 0.000%

    No Known Activations