© 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. 6266
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    Negative Logits
    enderror
    -0.44
     tưởng
    -0.44
    MLLoader
    -0.41
    atiles
    -0.38
    رشف
    -0.38
     chú
    -0.37
    UMBUS
    -0.35
     ens
    -0.35
    gnus
    -0.35
    qa
    -0.35
    POSITIVE LOGITS
     MatDialog
    0.62
     censiti
    0.61
    MeasureSpec
    0.59
     hObject
    0.59
     Rationale
    0.58
     "..\..\..\
    0.56
     couvre
    0.55
    Style
    0.54
    CMYK
    0.54
    ORCID
    0.54
    Activations Density 0.005%

    No Known Activations