© 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. 20-CLT-HP
    7. 72953
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ⓧ
    -0.80
     nakalista
    -0.69
    complexContent
    -0.67
    adpleegd
    -0.66
     autorytatywna
    -0.65
    OrBuilder
    -0.65
     CURIAM
    -0.64
    ConstraintMaker
    -0.63
    IsContent
    -0.63
     ***!
    -0.62
    POSITIVE LOGITS
    Rihanna
    0.40
     dessins
    0.39
     winter
    0.39
    Abit
    0.37
    gesch
    0.37
    sikker
    0.36
     ri
    0.36
    Ine
    0.35
     bundes
    0.35
    Nosotros
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.