© 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. 77933
    Prev
    Next
    INDEX
    Explanations

    chemicals

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ModelSerializer
    -0.73
     transférez
    -0.69
    +#+#
    -0.65
     ویکی‌پدی
    -0.62
     فريبيس
    -0.58
     pinulongan
    -0.58
    AndEndTag
    -0.57
    synthesize
    -0.57
     AssemblyCulture
    -0.56
    afu
    -0.55
    POSITIVE LOGITS
     Dic
    0.52
     dic
    0.51
     ch
    0.51
     للمعارف
    0.48
    Ch
    0.46
     chí
    0.45
     Ch
    0.45
    OCI
    0.44
     hypoch
    0.43
    Ч
    0.41
    Activations Density 0.005%

    No Known Activations