© 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. 72290
    Prev
    Next
    INDEX
    Explanations

    Eye and vision issues

    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
     OH
    -0.49
     stan
    -0.47
     du
    -0.47
    ret
    -0.47
     w
    -0.47
     py
    -0.46
     Rud
    -0.45
    тя
    -0.45
     Tr
    -0.45
    angled
    -0.45
    POSITIVE LOGITS
    ::_('
    0.76
    +#+#
    0.71
    ✨:
    0.70
    bootstrapcdn
    0.65
     femininos
    0.63
    enderror
    0.63
     Italij
    0.62
     comigo
    0.62
     MainAxisSize
    0.58
    toContain
    0.58
    Activations Density 0.006%

    No Known Activations