© 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. 73187
    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
     estekak
    -0.61
    __*/
    -0.60
     Mej
    -0.60
     MPL
    -0.59
     awakeFromNib
    -0.59
    Xna
    -0.58
    IsContent
    -0.57
    /*
    -0.56
    enumi
    -0.54
     كومونز
    -0.54
    POSITIVE LOGITS
     vanishing
    0.71
     leading
    0.70
     rule
    0.68
     Leading
    0.67
     horizon
    0.66
     Rule
    0.65
    leading
    0.63
    Leading
    0.58
     Van
    0.57
     lead
    0.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.