© 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. 0-CLT-HP
    7. 38916
    Prev
    Next
    INDEX
    Explanations

    articles/webpages

    np_max-act · gemini-2.0-flash
    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
     Re
    -0.68
     
    -0.67
     d
    -0.67
     F
    -0.63
     m
    -0.63
     T
    -0.63
     sus
    -0.61
     R
    -0.61
     ac
    -0.61
    <eos>
    -0.60
    POSITIVE LOGITS
     myſelf
    1.63
     Efq
    1.59
     Jefus
    1.50
     itſelf
    1.48
     houſe
    1.46
     Monfieur
    1.46
     pleaſure
    1.45
     purpoſe
    1.41
     Majefty
    1.38
     iſt
    1.35
    Activations Density 0.377%

    No Known Activations