© 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. 95194
    Prev
    Next
    INDEX
    Explanations

    awards and trademarks

    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
     Rescue
    -0.88
     Bands
    -0.84
     rescue
    -0.84
    Rescue
    -0.76
     rescued
    -0.75
     rescues
    -0.71
    OGND
    -0.70
     bands
    -0.69
    ections
    -0.68
    Bands
    -0.67
    POSITIVE LOGITS
    ness
    0.59
    way
    0.55
    ValueStyle
    0.52
    бут
    0.48
    ностью
    0.46
    metis
    0.46
    uitton
    0.43
     ways
    0.43
    Expedia
    0.43
    arrêt
    0.42
    Activations Density 0.036%

    No Known Activations