© 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. 9319
    Prev
    Next
    INDEX
    Explanations

    Obsession

    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
    SourceChecksum
    -0.79
     disambiguazione
    -0.56
    l
    -0.54
     beneath
    -0.53
    RegistryLite
    -0.53
     Beneath
    -0.52
    r
    -0.52
    iom
    -0.52
    at
    -0.52
    m
    -0.51
    POSITIVE LOGITS
    phazard
    0.61
    ainville
    0.53
     iprot
    0.52
    hammad
    0.52
     doInBackground
    0.52
    NUMX
    0.52
     pajero
    0.51
     Electoral
    0.50
    Bảo
    0.50
    lectoral
    0.50
    Activations Density 0.042%

    No Known Activations