© 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. 5-CLT-HP
    7. 91148
    Prev
    Next
    INDEX
    Explanations

    call

    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
     dead
    -0.60
     enim
    -0.54
    ICAL
    -0.54
    lden
    -0.51
     it
    -0.50
    vne
    -0.49
    jel
    -0.49
     za
    -0.48
    ля
    -0.48
    lima
    -0.47
    POSITIVE LOGITS
    ISupport
    0.71
    клопе
    0.62
     snippetHide
    0.59
    WebVitals
    0.59
     demografica
    0.56
    yntaxException
    0.56
    findpost
    0.55
    stdc
    0.54
     Spisak
    0.54
     Gator
    0.54
    Activations Density 0.000%

    No Known Activations