© 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. 4-CLT-HP
    7. 605
    Prev
    Next
    INDEX
    Explanations

    +

    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
     estekak
    -0.87
    AsUp
    -0.65
     typelib
    -0.61
     betweenstory
    -0.60
     onPostExecute
    -0.58
     Superhosts
    -0.56
    GeneratedValue
    -0.56
     استنادى
    -0.56
    ResumeLayout
    -0.55
     McAllister
    -0.55
    POSITIVE LOGITS
    writeField
    0.61
    TRAILING
    0.55
    homonymie
    0.48
    DRY
    0.46
    readFileSync
    0.46
    astify
    0.45
    firestore
    0.44
    อยู่
    0.44
    providedIn
    0.43
    oflavin
    0.43
    Activations Density 0.001%

    No Known Activations