© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9404
    Prev
    Next
    INDEX
    Explanations

    Day

    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
     beginnetje
    -0.86
    DockStyle
    -0.85
    chitis
    -0.82
     متعلقه
    -0.80
    Personensuche
    -0.77
    StructEnd
    -0.76
     HttpNotFound
    -0.75
    tagHelperRunner
    -0.73
     Савезне
    -0.69
     oprot
    -0.67
    POSITIVE LOGITS
     coopération
    0.51
     tramonto
    0.47
     causes
    0.46
     culturelle
    0.46
     cultuur
    0.46
     tetto
    0.45
     Tears
    0.45
     depuis
    0.45
     caused
    0.44
     bacio
    0.43
    Activations Density 0.038%

    No Known Activations