© 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. 95377
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     utafitiHapana
    -0.59
     وتسجيلات
    -0.54
     rêves
    -0.54
     évek
    -0.53
    Geografía
    -0.52
     déchir
    -0.51
     dépens
    -0.50
     Fuerzas
    -0.49
    saraba
    -0.48
    ísima
    -0.48
    POSITIVE LOGITS
    \{\\
    0.63
    IRQn
    0.56
    DNEY
    0.54
    __":
    0.54
    ⓘ
    0.54
    processable
    0.54
     acquainted
    0.52
     familiar
    0.51
     consumer
    0.51
    createCanvas
    0.51
    Activations Density 0.038%

    No Known Activations