© 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. 6007
    Prev
    Next
    INDEX
    Explanations

    ing

    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
     protoimpl
    -0.88
     "..\..\
    -0.85
     مشين
    -0.84
    SequentialGroup
    -0.82
     autorytatywna
    -0.81
    dbo
    -0.78
     виправивши
    -0.77
     "..\..\..\
    -0.76
    tagHelperRunner
    -0.76
     resourceCulture
    -0.75
    POSITIVE LOGITS
    <bos>
    0.87
     religieuses
    0.34
     változ
    0.33
     officiels
    0.30
     commerciaux
    0.29
     förslag
    0.29
     commerciales
    0.29
     sanitaires
    0.28
     devoirs
    0.27
     enfans
    0.27
    Activations Density 16.462%

    No Known Activations