© 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. 0-CLT-HP
    7. 42573
    Prev
    Next
    INDEX
    Explanations

    uthor

    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
    \{\\
    -0.80
    seamnă
    -0.60
    FieldBuilder
    -0.59
    دانشنامهٔ
    -0.59
     tithe
    -0.56
     PopupWindow
    -0.55
    principalColumn
    -0.54
     Putnam
    -0.53
     atracciones
    -0.52
    پیوند
    -0.52
    POSITIVE LOGITS
    BeginContext
    0.68
    Vidite
    0.61
    RefNanny
    0.48
    et
    0.46
    eez
    0.46
     ocasion
    0.46
    equilibrium
    0.45
    __*/
    0.44
    orino
    0.44
     चीज़ों
    0.44
    Activations Density 0.028%

    No Known Activations