© 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. 44203
    Prev
    Next
    INDEX
    Explanations

    Atkins

    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
     
    -0.60
    ,
    -0.58
    igt
    -0.55
    ↵
    -0.55
     den
    -0.53
     top
    -0.52
     (
    -0.51
    ist
    -0.50
     Re
    -0.50
     a
    -0.49
    POSITIVE LOGITS
     Majefty
    1.68
     Monfieur
    1.63
     myſelf
    1.61
     itſelf
    1.57
     Jefus
    1.55
     pleaſure
    1.53
    ſelf
    1.48
     Houſe
    1.43
     purpoſe
    1.43
     themſelves
    1.41
    Activations Density 0.121%

    No Known Activations