© 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. 1-CLT-HP
    7. 9279
    Prev
    Next
    INDEX
    Explanations

    Relationships

    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
    +#+#
    -0.48
     his
    -0.48
     or
    -0.47
     كومونز
    -0.46
    SYNOPSIS
    -0.43
    ஞ்ச
    -0.42
    photobucket
    -0.42
     mix
    -0.41
    accia
    -0.41
    SceneManagement
    -0.39
    POSITIVE LOGITS
     pinulongan
    0.78
    InjectAttribute
    0.73
    diers
    0.65
    Rè
    0.64
     autorytatywna
    0.64
     TextAppearance
    0.64
    esez
    0.63
    RTSC
    0.63
    RectangleBorder
    0.63
    клопе
    0.63
    Activations Density 0.008%

    No Known Activations