© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3796
    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
     mola
    -0.52
     skr
    -0.52
    γχ
    -0.49
    kolog
    -0.48
    تج
    -0.47
     lumi
    -0.47
     armen
    -0.47
    ]--;
    -0.47
    piri
    -0.46
     idiot
    -0.45
    POSITIVE LOGITS
    CloseOperation
    0.70
     antaranya
    0.63
    httphttps
    0.62
    phanumeric
    0.62
    PYX
    0.59
    RTDA
    0.59
    DockStyle
    0.58
    cookieParser
    0.57
    Хьажоргаш
    0.57
    CodeAttribute
    0.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.