© 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. 5-CLT-HP
    7. 5387
    Prev
    Next
    INDEX
    Explanations

    Sacramento, California

    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
    исленность
    -0.77
     AssemblyCulture
    -0.76
    windowFixed
    -0.68
    EDEFAULT
    -0.67
     resourceCulture
    -0.67
    AndEndTag
    -0.66
    expandindo
    -0.66
    featureID
    -0.65
     muualla
    -0.65
    SBATCH
    -0.62
    POSITIVE LOGITS
     Bee
    0.46
    st
    0.45
    atora
    0.44
    tvguidetime
    0.44
    itura
    0.43
    cosa
    0.42
     bản
    0.42
     derr
    0.42
     maris
    0.41
    uls
    0.41
    Activations Density 0.001%

    No Known Activations