© 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. 10319
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous texts

    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
     down
    -0.39
    TintMode
    -0.36
    Kamu
    -0.36
     hoc
    -0.36
     become
    -0.35
     import
    -0.35
     aven
    -0.35
    Diweddarwch
    -0.33
    Down
    -0.33
     imply
    -0.33
    POSITIVE LOGITS
     Theſe
    0.74
    contentLoaded
    0.74
    tonsoft
    0.72
     Monfieur
    0.71
    inSlope
    0.70
    <?
    0.69
     Epif
    0.68
    Demografía
    0.67
    bukkit
    0.67
    Portale
    0.67
    Activations Density 0.013%

    No Known Activations