© 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. 8977
    Prev
    Next
    INDEX
    Explanations

    ged

    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
     bezeichneter
    -0.68
    alnız
    -0.64
     HttpNotFound
    -0.63
    ^(@)
    -0.62
    <bos>
    -0.62
     itſelf
    -0.61
    ."]
    -0.61
     themſelves
    -0.60
    NUMX
    -0.58
    /]
    -0.58
    POSITIVE LOGITS
    a
    0.82
    e
    0.75
    o
    0.67
    i
    0.66
    Rhestr
    0.62
    ه
    0.62
    oven
    0.61
    y
    0.60
    ibo
    0.56
    WebElementEntity
    0.56
    Activations Density 0.001%

    No Known Activations