© 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. 72267
    Prev
    Next
    INDEX
    Explanations

    user

    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
     متعلقه
    -0.76
    thâu
    -0.59
    ConstraintMaker
    -0.58
     ErrIntOverflow
    -0.52
    setScene
    -0.52
     quadrangle
    -0.52
     viewWillAppear
    -0.52
    出版年
    -0.52
     JpaRepository
    -0.50
    makeConstraints
    -0.50
    POSITIVE LOGITS
    ISupport
    0.52
    Попис
    0.50
    modi
    0.46
    Land
    0.46
    ops
    0.44
    hoeddwyd
    0.44
    ادگی
    0.43
     distanciation
    0.43
     agenti
    0.42
     старости
    0.42
    Activations Density 0.001%

    No Known Activations