© 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. 0-CLT-HP
    7. 95409
    Prev
    Next
    INDEX
    Explanations

    period

    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
    .
    -1.33
    ,
    -1.02
     so
    -0.85
    :
    -0.81
    -
    -0.76
     in
    -0.73
     a
    -0.73
     for
    -0.73
     on
    -0.72
     as
    -0.72
    POSITIVE LOGITS
     Theſe
    1.58
    AndEndTag
    1.41
     Monfieur
    1.36
     itſelf
    1.35
     myſelf
    1.32
     ་་
    1.31
    parsedMessage
    1.30
     Efq
    1.28
     tartalomajánló
    1.24
    expandindo
    1.23
    Activations Density 3.533%

    No Known Activations