© 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. 95464
    Prev
    Next
    INDEX
    Explanations

    pack

    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
     packs
    -2.36
     pack
    -1.95
     Packs
    -1.86
    packs
    -1.49
    Packs
    -1.39
     Pack
    -1.18
     PACK
    -1.13
     packets
    -1.07
    pack
    -1.01
    Pack
    -0.92
    POSITIVE LOGITS
     الدولى
    0.57
    lapping
    0.56
    AndEndTag
    0.53
    cama
    0.51
    IFYING
    0.50
    plevel
    0.50
    ceğim
    0.50
    apunov
    0.50
     Autorizaciones
    0.49
    signing
    0.49
    Activations Density 0.359%

    No Known Activations