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. 11221
    Prev
    Next
    INDEX
    Explanations

    before

    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
     the
    -0.78
     a
    -0.58
     He
    -0.54
     our
    -0.50
     he
    -0.50
     
    -0.50
     those
    -0.49
     F
    -0.49
     they
    -0.49
     someone
    -0.48
    POSITIVE LOGITS
     comigo
    0.74
     Efq
    0.71
     uſed
    0.68
    getRuntime
    0.66
    agissait
    0.65
     raiſ
    0.64
     doubtnut
    0.64
     downloaded
    0.63
     متعلقه
    0.63
    évaluateur
    0.63
    Activations Density 0.068%

    No Known Activations