© 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. 94890
    Prev
    Next
    INDEX
    Explanations

    written

    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
    MigrationBuilder
    -0.90
    /**
    -0.79
    heads
    -0.78
     kasarigan
    -0.76
     विश्वसनीयता
    -0.75
     betweenstory
    -0.72
     utafitiHapana
    -0.71
     ModelExpression
    -0.70
    writeFieldEnd
    -0.70
    
    -0.69
    POSITIVE LOGITS
    ----</
    0.50
     pauvres
    0.47
     similaires
    0.47
     variés
    0.46
     confirmer
    0.46
     halv
    0.45
     suficientes
    0.45
    bija
    0.43
     kapcs
    0.43
    agna
    0.43
    Activations Density 0.165%

    No Known Activations