© 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. 1-CLT-HP
    7. 8968
    Prev
    Next
    INDEX
    Explanations

    Acts and application

    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
     snippetHide
    -0.85
     lenker
    -0.84
    adpleegd
    -0.68
    tagHelperRunner
    -0.65
    Hozzáférés
    -0.64
    MemoryWarning
    -0.64
    +#+
    -0.64
    InjectAttribute
    -0.63
    flashdata
    -0.63
     ITIS
    -0.62
    POSITIVE LOGITS
     églises
    0.58
     publiques
    0.49
     Regno
    0.49
     démocr
    0.49
     religieuses
    0.49
     chré
    0.49
     ordres
    0.48
     vaisseaux
    0.48
     cavalli
    0.47
     dieux
    0.47
    Activations Density 0.012%

    No Known Activations