© 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. 4-CLT-HP
    7. 108
    Prev
    Next
    INDEX
    Explanations

    INFL

    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
     disambiguazione
    -1.11
    sizeCache
    -1.00
     (−
    -0.94
    !—
    -0.84
     intptr
    -0.83
     (+
    -0.82
     (+)
    -0.82
     (~
    -0.82
    تقاوى
    -0.80
    '...
    -0.79
    POSITIVE LOGITS
     vicini
    0.32
     থেকে
    0.31
     to
    0.31
    ByUsername
    0.30
     spre
    0.30
     های
    0.29
     so
    0.28
     sonore
    0.28
     me
    0.27
     به
    0.26
    Activations Density 0.006%

    No Known Activations