© 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. 77399
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     genitori
    -0.50
     acestei
    -0.50
     profundos
    -0.49
     quelcon
    -0.48
     domésticos
    -0.48
     normaux
    -0.47
     verdaderas
    -0.47
     tradicionais
    -0.47
     ongles
    -0.46
     profondeur
    -0.46
    POSITIVE LOGITS
     MainAxisSize
    0.75
    GraphicsUnit
    0.75
     تضيفلها
    0.74
    principalTable
    0.73
     onAnimation
    0.73
     שוליים
    0.72
     GenerationType
    0.71
     <=",
    0.69
    ThroughAttribute
    0.68
     ModelExpression
    0.67
    Activations Density 0.000%

    No Known Activations