© 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. 10111
    Prev
    Next
    INDEX
    Explanations

    s

    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
    rungsseite
    -0.71
     Wiktionnaire
    -0.68
    PhysRevD
    -0.65
    liothèque
    -0.60
    orithmic
    -0.59
    ","#
    -0.58
    writeFieldEnd
    -0.58
    chiat
    -0.58
    بوابة
    -0.58
    franch
    -0.57
    POSITIVE LOGITS
    ’
    0.57
    `
    0.52
     sounds
    0.52
    (
    0.51
     facts
    0.50
    ”
    0.49
     conditions
    0.47
    SourceChecksum
    0.47
    cam
    0.46
    amo
    0.46
    Activations Density 0.055%

    No Known Activations