© 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. 45178
    Prev
    Next
    INDEX
    Explanations

    against

    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
     against
    -1.66
    against
    -1.45
     Against
    -1.23
    Against
    -1.23
     AGAINST
    -1.11
     contre
    -0.93
     terhadap
    -0.80
     versus
    -0.79
     gegen
    -0.76
     tegen
    -0.74
    POSITIVE LOGITS
    ++
    0.56
     confirmation
    0.56
     Confirmation
    0.55
    :%.
    0.55
    Spoljašnje
    0.55
     stanovnika
    0.54
    _
    0.54
     amnesty
    0.54
    angering
    0.54
     positions
    0.53
    Activations Density 0.049%

    No Known Activations