© 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. 74665
    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
     Italijani
    -0.75
     FixedUpdate
    -0.73
     Wikimedijinoj
    -0.73
     correctes
    -0.72
    #+#
    -0.72
    riwal
    -0.71
    TagHelper
    -0.71
     gynhyrchwyd
    -0.70
    InputBorder
    -0.69
     jsPsych
    -0.68
    POSITIVE LOGITS
     S
    0.43
     X
    0.41
     conf
    0.38
    XmlAccessorType
    0.36
     x
    0.34
     dist
    0.34
    ofus
    0.33
    S
    0.31
    putExtra
    0.31
    ūd
    0.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.