© 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. 90829
    Prev
    Next
    INDEX
    Explanations

    -

    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
    Negative Logits
    rostis
    -0.60
     Tense
    -0.56
    RT
    -0.55
     RT
    -0.55
    urgie
    -0.54
    Ruf
    -0.52
    umus
    -0.50
    NCT
    -0.49
    limus
    -0.49
     Tzu
    -0.49
    POSITIVE LOGITS
     initComponents
    0.54
     estimés
    0.54
    jahtera
    0.54
    AndEndTag
    0.53
    WriteLiteral
    0.49
    Kjelder
    0.47
    ah
    0.47
    addPreferredGap
    0.47
    astéro
    0.46
     negru
    0.45
    Activations Density 0.001%

    No Known Activations