© 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. 1-CLT-HP
    7. 10338
    Prev
    Next
    INDEX
    Explanations

    science fiction

    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
     Pant
    -0.87
     pant
    -0.75
    pant
    -0.75
    Pant
    -0.68
    prechpartner
    -0.66
     Cuff
    -0.62
     cuff
    -0.60
    quiao
    -0.60
    styleType
    -0.59
    lorette
    -0.56
    POSITIVE LOGITS
    SerializedSize
    0.52
    ₦
    0.46
    Aran
    0.46
    ้าง
    0.45
    philips
    0.45
    UnitTesting
    0.45
    stein
    0.45
    لينكات
    0.44
    schmidt
    0.44
    Ори
    0.43
    Activations Density 0.079%

    No Known Activations