© 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. 78037
    Prev
    Next
    INDEX
    Explanations

    ’

    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
     doInBackground
    -0.51
     wikipagina
    -0.46
    pushFollow
    -0.45
     pageNum
    -0.41
    DataAnnotations
    -0.41
     tuổi
    -0.40
    движи
    -0.40
     deep
    -0.39
    коп
    -0.39
     twelfth
    -0.39
    POSITIVE LOGITS
    nezeu
    0.64
    adpleegd
    0.59
    LEncoder
    0.58
     مشين
    0.57
    concel
    0.56
    ніципа
    0.55
    OuterClass
    0.55
    PreferredItem
    0.55
    DispatchToProps
    0.54
    yntaxException
    0.54
    Activations Density 0.000%

    No Known Activations