© 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. 0-CLT-HP
    7. 43420
    Prev
    Next
    INDEX
    Explanations

    computing and technology

    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
    WebElementEntity
    -0.66
    ⓧ
    -0.59
    ἶ
    -0.57
    cooperation
    -0.56
    international
    -0.56
    issex
    -0.56
    agreed
    -0.54
    bekah
    -0.53
     Drag
    -0.53
    ̍t
    -0.52
    POSITIVE LOGITS
    runApp
    0.66
    store
    0.61
    site
    0.56
    viembre
    0.54
    station
    0.54
     utafitiHapana
    0.54
    StoryboardSegue
    0.53
     raiſ
    0.52
    ns
    0.52
    ga
    0.52
    Activations Density 0.314%

    No Known Activations