© 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. 1-CLT-HP
    7. 9031
    Prev
    Next
    INDEX
    Explanations

    Hughes

    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
     Hughes
    -1.38
    Hughes
    -1.12
     HUGH
    -0.81
    ching
    -0.77
    numerusform
    -0.51
     Borel
    -0.49
    CDF
    -0.49
    <bos>
    -0.48
     plotted
    -0.48
    issa
    -0.47
    POSITIVE LOGITS
     виправивши
    0.73
     bpy
    0.63
    gdx
    0.62
     transfieras
    0.60
    ukone
    0.59
    IsContent
    0.58
     שוליים
    0.58
    EndProject
    0.58
     besök
    0.58
    enumii
    0.58
    Activations Density 0.017%

    No Known Activations