© 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. 94269
    Prev
    Next
    INDEX
    Explanations

    locations/situations

    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
     glyphicon
    -0.49
     لينك
    -0.49
    ων
    -0.46
     Hamlet
    -0.46
     salts
    -0.45
    tsi
    -0.45
     linkovi
    -0.43
     drafts
    -0.43
    riwal
    -0.43
    ally
    -0.42
    POSITIVE LOGITS
    adaptiveStyles
    0.64
    клопе
    0.60
     themſelves
    0.60
    ſelves
    0.57
    Autoritní
    0.57
     miljoner
    0.57
    WriteTagHelper
    0.56
     Majefty
    0.56
    BRARY
    0.56
     saites
    0.56
    Activations Density 0.844%

    No Known Activations