© 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. 604
    Prev
    Next
    INDEX
    Explanations

    from

    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
    最快更新
    -0.61
    رشف
    -0.55
     introducing
    -0.50
    piram
    -0.49
     exposing
    -0.47
     subjecting
    -0.47
    ]={
    -0.46
     putting
    -0.45
     wagen
    -0.45
    adding
    -0.45
    POSITIVE LOGITS
     inside
    0.63
    sidemargin
    0.57
     behind
    0.57
    ^(@)
    0.57
     beneath
    0.56
    ArgumentParser
    0.56
    ScopeManager
    0.56
    StoryboardSegue
    0.54
    PrototypeOf
    0.53
     there
    0.52
    Activations Density 0.008%

    No Known Activations