© 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. 8999
    Prev
    Next
    INDEX
    Explanations

    gn

    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
    gn
    -2.34
    gne
    -1.91
    gni
    -1.70
    gna
    -1.70
    gno
    -1.52
    gnes
    -1.52
    gnat
    -1.35
    GN
    -1.34
    gner
    -1.21
    gnan
    -1.16
    POSITIVE LOGITS
    Geplaatst
    0.69
    esez
    0.68
     tartalomajánló
    0.65
    ueling
    0.63
     الحره
    0.63
     Jefus
    0.63
     Monfieur
    0.62
     Majefty
    0.61
     Reſ
    0.60
     ſche
    0.60
    Activations Density 0.016%

    No Known Activations