© 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. 93883
    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
    URA
    -0.52
     πυ
    -0.48
    ura
    -0.48
    Begriffsklä
    -0.47
     Inventory
    -0.47
     mantan
    -0.47
    Inventory
    -0.47
    hamad
    -0.46
     Bauch
    -0.45
     hin
    -0.45
    POSITIVE LOGITS
    Hentet
    0.76
    MLLoader
    0.76
     Signalez
    0.74
    RenderAtEndOf
    0.73
    Referanser
    0.70
     المعيارى
    0.68
    ftagPool
    0.68
     wireType
    0.66
     MainAxisSize
    0.66
    Autoritní
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.