© 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. 1-CLT-HP
    7. 15888
    Prev
    Next
    INDEX
    Explanations

    Curry

    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
    REE
    -1.02
    ocrat
    -0.60
     seem
    -0.52
    anker
    -0.48
    Ông
    -0.48
     seems
    -0.46
     both
    -0.45
     figures
    -0.44
     double
    -0.44
    queles
    -0.44
    POSITIVE LOGITS
     nahilalakip
    1.08
    SourceChecksum
    0.92
    AndEndTag
    0.91
    TagMode
    0.82
    complexContent
    0.79
     nakalista
    0.78
    出版年
    0.77
    RectangleBorder
    0.76
    SequentialGroup
    0.75
     виправивши
    0.75
    Activations Density 0.043%

    No Known Activations