© 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. 92636
    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
     saites
    -0.91
     defStyleAttr
    -0.79
    \"");
    -0.78
    IsContent
    -0.77
    lottes
    -0.76
    ConstraintMaker
    -0.72
    hoeddwyd
    -0.68
     >=",
    -0.68
    WaitGroup
    -0.67
    readFileSync
    -0.66
    POSITIVE LOGITS
    actual
    0.48
    هو
    0.46
    ACTUAL
    0.45
    Santis
    0.44
    DialogInterface
    0.44
    truly
    0.44
    Allowed
    0.43
     punggung
    0.43
     façons
    0.42
    …………………………………………
    0.42
    Activations Density 0.005%

    No Known Activations