© 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. 72063
    Prev
    Next
    INDEX
    Explanations

    technical/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
    లాలు
    -0.73
     MainAxisSize
    -0.69
    معلومات
    -0.61
     cherchés
    -0.61
    adaptiveStyles
    -0.58
     BoxFit
    -0.57
    chute
    -0.57
    StoryboardSegue
    -0.57
    itinéraire
    -0.57
    Pranala
    -0.57
    POSITIVE LOGITS
     find
    0.69
     finds
    0.52
     finding
    0.52
     one
    0.52
     end
    0.51
     fi
    0.50
     slow
    0.49
     End
    0.46
    EndTag
    0.45
     nd
    0.44
    Activations Density 0.000%

    No Known Activations