© 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. 20-CLT-HP
    7. 76904
    Prev
    Next
    INDEX
    Explanations

    General

    np_max-act-logits · 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
     Chancery
    -0.58
    новниш
    -0.57
    KURZBESCHREIBUNG
    -0.56
     Galbraith
    -0.54
     aikaa
    -0.54
    ToDelete
    -0.53
    delin
    -0.53
    φε
    -0.52
     mukana
    -0.52
    Hauptartikel
    -0.52
    POSITIVE LOGITS
     للمعارف
    0.55
    UserScript
    0.54
    autoload
    0.50
     préférences
    0.49
     snippetHide
    0.47
    StoryboardSegue
    0.47
     Initialized
    0.46
     IndexPath
    0.46
     Awareness
    0.45
     SCIENCE
    0.45
    Activations Density 0.004%

    No Known Activations