© 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. 5-CLT-HP
    7. 91925
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
     sebut
    -0.56
    ellos
    -0.50
    InputGroup
    -0.50
    IntoConstraints
    -0.50
    mä
    -0.49
    اظ
    -0.48
     on
    -0.48
    hoven
    -0.47
    acyj
    -0.47
    sizePolicy
    -0.46
    POSITIVE LOGITS
     propOrder
    0.73
     the
    0.70
     preserving
    0.65
     betweenstory
    0.64
    __',
    0.60
     الحره
    0.60
    OGND
    0.57
     having
    0.57
     exploiting
    0.57
     ensuring
    0.57
    Activations Density 0.000%

    No Known Activations