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. 12863
    Prev
    Next
    INDEX
    Explanations

    justifications and arguments

    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
    ROLS
    -0.56
    writeFieldEnd
    -0.52
     rudi
    -0.52
    WebElementEntity
    -0.51
    verifyException
    -0.49
    новништво
    -0.46
    ClientRect
    -0.46
     onCreateView
    -0.45
    GeneratedMessage
    -0.45
    kede
    -0.45
    POSITIVE LOGITS
    béco
    0.65
     mentales
    0.60
    AllowAnonymous
    0.57
    ADELPHIA
    0.56
     stanga
    0.53
    ContextHolder
    0.52
    ंत्री
    0.50
    obiety
    0.50
     Belgique
    0.48
     fleste
    0.48
    Activations Density 0.027%

    No Known Activations