© 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. 20-CLT-HP
    7. 75450
    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
    άσ
    -0.61
    tagHelperRunner
    -0.61
     jadx
    -0.57
     MonoBehaviour
    -0.56
    essoal
    -0.55
    Cyfeiriadau
    -0.55
     Cristina
    -0.53
    شهاد
    -0.53
    Hauptartikel
    -0.52
     فريبيس
    -0.51
    POSITIVE LOGITS
    Orion
    0.59
    IsInitialized
    0.57
     Sunset
    0.51
     Baillargeon
    0.49
     Orion
    0.49
     Budget
    0.48
    Sunset
    0.47
    ondheim
    0.46
    ભ
    0.44
     Italijani
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.