© 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. 75292
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
    Hentet
    -0.43
     للاسماء
    -0.42
    DoubleQuotes
    -0.41
    RenderAtEndOf
    -0.41
    🅽
    -0.39
    Personendaten
    -0.39
     distanciation
    -0.37
    artements
    -0.37
     tope
    -0.37
     Максима
    -0.36
    POSITIVE LOGITS
     
    1.46
     about
    1.11
     ~
    0.98
     .
    0.93
     around
    0.91
     ∼
    0.90
     apie
    0.83
    about
    0.81
     tungkol
    0.79
     alrededor
    0.78
    Activations Density 0.005%

    No Known Activations