© 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. 91564
    Prev
    Next
    INDEX
    Explanations

    s

    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
     NUKAT
    -0.73
     nahilalakip
    -0.68
    Identyfik
    -0.67
     Administrativna
    -0.65
     дописавши
    -0.64
    AsUp
    -0.63
     estekak
    -0.61
    Autoritní
    -0.60
     correctes
    -0.60
     ویکی‌پدی
    -0.59
    POSITIVE LOGITS
    BorderSize
    0.43
     still
    0.42
     something
    0.39
    kar
    0.39
     at
    0.39
     I
    0.39
    charAt
    0.39
    міністра
    0.38
    mola
    0.38
    ni
    0.37
    Activations Density 0.010%

    No Known Activations