© 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. 666
    Prev
    Next
    INDEX
    Explanations

    text formatting

    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
     iconTwitter
    -0.42
    irst
    -0.41
     newBuilder
    -0.39
     '\\;'
    -0.39
    onPause
    -0.38
    Diweddarwch
    -0.36
     dew
    -0.34
     Uw
    -0.34
    <bos>
    -0.34
    PEAT
    -0.34
    POSITIVE LOGITS
    XMLSchema
    0.81
    ConstraintMaker
    0.78
    msgTypes
    0.72
     محفوظة
    0.70
    PointerException
    0.66
    epik
    0.65
     handker
    0.63
     splashes
    0.61
    himovic
    0.61
    bolista
    0.60
    Activations Density 0.024%

    No Known Activations