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. 0-CLT-HP
    4. 4
    Prev
    Next
    INDEX
    Explanations

    solubility

    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
     itſelf
    -1.12
    ſelf
    -1.05
     Jefus
    -1.03
     purpoſe
    -1.02
     Efq
    -1.02
     myſelf
    -0.99
     chofe
    -0.94
     prevailed
    -0.93
     pleaſure
    -0.93
     raiſ
    -0.91
    POSITIVE LOGITS
     [
    0.57
     a
    0.56
     the
    0.55
     an
    0.55
     set
    0.54
    <eos>
    0.52
     setting
    0.52
    ,
    0.52
     both
    0.52
     events
    0.51
    Activations Density 0.017%

    No Known Activations