© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74686
    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
    DeleteBehavior
    -0.76
     transfieras
    -0.75
     ProtoMessage
    -0.75
    principalTable
    -0.75
     to
    -0.68
    (!__
    -0.68
     protoimpl
    -0.67
     propOrder
    -0.67
     KeyError
    -0.65
    رشف
    -0.65
    POSITIVE LOGITS
     part
    0.52
     onderdeel
    0.48
    +#+#
    0.47
    tingly
    0.45
     kasarigan
    0.43
    Firebase
    0.36
    álat
    0.35
     ciepła
    0.34
    νά
    0.34
    velmente
    0.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.