© 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. 5-CLT-HP
    7. 2137
    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
    IntoConstraints
    -0.71
    enumi
    -0.69
    __':
    -0.67
     تانيه
    -0.64
     UIKit
    -0.62
    алу
    -0.60
    expandindo
    -0.58
    TypedDataSet
    -0.58
     IBOutlet
    -0.57
    AndEndTag
    -0.57
    POSITIVE LOGITS
     vérifier
    0.47
     Crow
    0.46
    WriteBarrier
    0.44
    MoveNext
    0.44
    setta
    0.44
    itica
    0.43
     Ghat
    0.43
     dựa
    0.43
    demic
    0.43
     Moy
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.