© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78259
    Prev
    Next
    INDEX
    Explanations

    free

    np_max-act-logits · 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
    Negative Logits
    WireFormat
    -0.68
    #+#
    -0.65
    AndroidJUnit
    -0.59
    AntiForgeryToken
    -0.58
    RenderAtEndOf
    -0.58
    localctx
    -0.57
    cshtml
    -0.56
    __':
    -0.55
    ClientSize
    -0.54
    argout
    -0.54
    POSITIVE LOGITS
     free
    1.23
    free
    0.95
     Free
    0.79
    Free
    0.72
     FREE
    0.69
     freien
    0.67
    frees
    0.63
     gratis
    0.62
     freie
    0.62
    FREE
    0.60
    Activations Density 0.003%

    No Known Activations