Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74365
    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
     sürd
    -0.45
     ***!
    -0.45
     Bibliothèque
    -0.44
    roek
    -0.44
     EnglishChoose
    -0.43
    __*/
    -0.42
     situe
    -0.42
    rumah
    -0.42
     تانيه
    -0.41
    묻
    -0.41
    POSITIVE LOGITS
     spawn
    0.68
     hob
    0.66
     crimp
    0.63
    IndentedString
    0.63
    ergies
    0.63
     gum
    0.62
    verifyException
    0.61
    NOPQRST
    0.60
     gawas
    0.60
     up
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.