Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12729
    Prev
    Next
    INDEX
    Explanations

    Latin

    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
    tvguidetime
    -1.07
     autorytatywna
    -0.79
    EDEFAULT
    -0.74
     Normdatei
    -0.72
    PerformLayout
    -0.68
    LATIN
    -0.64
    HasForeignKey
    -0.64
    findpost
    -0.63
    djangoproject
    -0.61
     resourceCulture
    -0.60
    POSITIVE LOGITS
    ate
    0.62
    nel
    0.59
    ation
    0.59
    ic
    0.58
     Nymp
    0.57
    us
    0.54
    mable
    0.54
     Renew
    0.54
     gant
    0.53
    ore
    0.53
    Activations Density 0.009%

    No Known Activations