© 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. 38942
    Prev
    Next
    INDEX
    Explanations

    Heather

    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
     myſelf
    -1.54
     itſelf
    -1.48
     Monfieur
    -1.41
     pleaſure
    -1.35
     ſche
    -1.30
     Jefus
    -1.30
     houſe
    -1.28
     Efq
    -1.28
     ſtate
    -1.26
     themſelves
    -1.24
    POSITIVE LOGITS
     d
    0.52
     il
    0.52
     co
    0.51
     Mac
    0.50
     w
    0.49
     t
    0.48
    tir
    0.48
     et
    0.48
     T
    0.48
     ver
    0.48
    Activations Density 0.149%

    No Known Activations