© 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. 90941
    Prev
    Next
    INDEX
    Explanations

    biological

    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
     itſelf
    -1.39
     myſelf
    -1.38
    ſelf
    -1.34
    ſelves
    -1.33
     Jefus
    -1.33
     Efq
    -1.27
     greateſt
    -1.27
     houſe
    -1.27
     themſelves
    -1.26
     Shakspeare
    -1.26
    POSITIVE LOGITS
     
    0.59
     pro
    0.58
    ,
    0.57
     and
    0.55
     in
    0.52
     of
    0.52
     (
    0.50
     on
    0.49
     St
    0.48
     Pro
    0.46
    Activations Density 0.135%

    No Known Activations