© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92391
    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
    ⓧ
    -0.67
     createState
    -0.61
    تقاوى
    -0.57
    SourceChecksum
    -0.54
    SharedCtor
    -0.54
    matchCondition
    -0.54
    __))
    -0.53
     defaultstate
    -0.50
    :+:
    -0.50
    EDEFAULT
    -0.49
    POSITIVE LOGITS
    Int
    0.47
    Recall
    0.45
    ISupport
    0.45
    Balance
    0.45
    Support
    0.44
    HashCode
    0.44
    gdx
    0.44
    CheckIn
    0.43
    Dep
    0.42
    Bail
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.