© 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. 20-CLT-HP
    7. 78149
    Prev
    Next
    INDEX
    Explanations

    Go

    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
    Negative Logits
    aarrggbb
    -0.59
     pinulongan
    -0.59
    TabStop
    -0.51
    StructEnd
    -0.51
    FFS
    -0.50
    appi
    -0.48
    FailureListener
    -0.46
    ghold
    -0.46
    ubar
    -0.46
     들
    -0.45
    POSITIVE LOGITS
     Administrativna
    0.66
    httphttps
    0.48
    Stain
    0.47
    __["
    0.46
     <<<<<<<<<<<<<<
    0.46
    XmlAccessType
    0.45
     estatu
    0.44
     Dafür
    0.44
    minimum
    0.43
     bậc
    0.42
    Activations Density 0.004%

    No Known Activations