© 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. 2207
    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
     ourselves
    -0.52
     little
    -0.52
     smooth
    -0.45
     maille
    -0.44
    RefNanny
    -0.43
     điệu
    -0.43
    ure
    -0.42
     Goodrich
    -0.42
     spot
    -0.42
     unknowns
    -0.42
    POSITIVE LOGITS
     للاسماء
    0.79
    Referencie
    0.78
     jsPsych
    0.69
    BagConstraints
    0.66
    ChildScrollView
    0.64
     they
    0.64
     propOrder
    0.64
    Зноскі
    0.63
     Committees
    0.63
     AssemblyTitle
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.