Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12945
    Prev
    Next
    INDEX
    Explanations

    ris

    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
    ris
    -2.28
    Ris
    -1.84
    RIS
    -1.73
     Ris
    -1.70
     ris
    -1.52
     RIS
    -1.20
    risi
    -1.00
    Risk
    -0.93
     Risk
    -0.93
    riss
    -0.92
    POSITIVE LOGITS
    WithIOException
    0.68
    UnsafeEnabled
    0.57
     beating
    0.56
    LookAnd
    0.53
    hyrchwyd
    0.51
     beat
    0.50
     Beat
    0.49
    bindingNavigator
    0.49
     beats
    0.49
    comuna
    0.48
    Activations Density 0.010%

    No Known Activations