© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91167
    Prev
    Next
    INDEX
    Explanations

    more

    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
     than
    -0.52
     GoogleFonts
    -0.48
    Rhestr
    -0.48
    zaamheid
    -0.48
    lawless
    -0.48
    tehen
    -0.47
    getDoctrine
    -0.47
     then
    -0.47
     collect
    -0.46
    rrggbb
    -0.46
    POSITIVE LOGITS
    SourceChecksum
    0.71
    
    0.60
    matchCondition
    0.59
    Legături
    0.59
    expandindo
    0.58
     nonUne
    0.57
    !
    0.57
    !")
    0.56
    StreetMap
    0.56
    URLException
    0.56
    Activations Density 0.001%

    No Known Activations