© 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. 930
    Prev
    Next
    INDEX
    Explanations

    common English words

    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
     Catawiki
    -0.68
    oredCriteria
    -0.62
    PerformLayout
    -0.60
    +#+
    -0.60
    ftagPool
    -0.59
     Италијани
    -0.54
    */),
    -0.53
    TestBed
    -0.53
    exels
    -0.52
    migrationBuilder
    -0.52
    POSITIVE LOGITS
     balance
    0.66
     lokasi
    0.63
     location
    0.61
     locatie
    0.59
     الحره
    0.58
     épis
    0.57
    MENAFN
    0.56
     étrangère
    0.54
    location
    0.54
     Schwer
    0.54
    Activations Density 0.002%

    No Known Activations