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. 12872
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     and
    -0.66
    providedIn
    -0.66
     批
    -0.60
     gewor
    -0.59
     şun
    -0.56
    awaiter
    -0.56
     iaitu
    -0.54
    そして
    -0.52
    and
    -0.52
    "]();
    -0.52
    POSITIVE LOGITS
     if
    0.61
     it
    0.59
     when
    0.59
     by
    0.55
     the
    0.55
     in
    0.53
     during
    0.52
     anytime
    0.52
     whenever
    0.52
     you
    0.51
    Activations Density 0.015%

    No Known Activations