© 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. 0-CLT-HP
    7. 95283
    Prev
    Next
    INDEX
    Explanations

    code

    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
    DllImport
    -0.64
     disambiguazione
    -0.62
    abestanden
    -0.59
     gärna
    -0.57
     onus
    -0.56
    CppMethod
    -0.55
    principalColumn
    -0.55
    endcsname
    -0.54
     faveur
    -0.52
     visibilité
    -0.51
    POSITIVE LOGITS
     bench
    0.60
    ‚¬
    0.55
     <>",
    0.54
    ijing
    0.52
    glDelete
    0.51
    ánd
    0.50
    bottomRight
    0.49
    Capit
    0.49
    neiden
    0.49
    ignac
    0.49
    Activations Density 1.485%

    No Known Activations