© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10646
    Prev
    Next
    INDEX
    Explanations

    0

    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
      
    -0.67
    <bos>
    -0.64
    AutoScaleMode
    -0.63
    EDEFAULT
    -0.57
     OFDb
    -0.56
     Hits
    -0.55
     $-
    -0.54
    afficheront
    -0.53
     Fits
    -0.53
    +#+#
    -0.53
    POSITIVE LOGITS
     JpaRepository
    0.54
    المناصب
    0.50
    PreAuthorize
    0.45
    KeySpec
    0.44
     /\.(
    0.44
    kelt
    0.43
    naires
    0.42
     ویکی‌پدیای
    0.41
    glPushMatrix
    0.41
    belline
    0.41
    Activations Density 0.007%

    No Known Activations