© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76667
    Prev
    Next
    INDEX
    Explanations

    words containing "short"

    np_max-act-logits · 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
     initComponents
    -0.75
     AssemblyCulture
    -0.71
    LLocation
    -0.69
    HostException
    -0.67
    httphttps
    -0.65
    хьтан
    -0.65
    omiast
    -0.65
    toplankton
    -0.64
     незавершена
    -0.63
     eventdata
    -0.62
    POSITIVE LOGITS
    ens
    0.57
    lic
    0.56
    out
    0.54
    enu
    0.54
    cu
    0.54
    zu
    0.50
    hir
    0.48
     out
    0.48
    ener
    0.48
    cuit
    0.48
    Activations Density 0.001%

    No Known Activations