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. 11085
    Prev
    Next
    INDEX
    Explanations

    im

    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
    ROP
    -0.57
    rop
    -0.50
    istic
    -0.50
    ,'\
    -0.49
     bev
    -0.47
     of
    -0.47
     thích
    -0.47
     cou
    -0.46
     bar
    -0.45
     b
    -0.45
    POSITIVE LOGITS
    sidemargin
    0.80
     وتسجيلات
    0.73
     Efq
    0.72
     跳转至
    0.71
    SBATCH
    0.70
    fjspx
    0.69
    (&:
    0.68
     AssemblyCulture
    0.67
    :✨
    0.66
    Aiheesta
    0.66
    Activations Density 0.177%

    No Known Activations