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. 20-CLT-HP
    4. 74075
    Prev
    Next
    INDEX
    Explanations

    points

    np_max-act-logits · 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
    webElementGuid
    -0.61
    ThemeOverlay
    -0.59
    ſelves
    -0.58
     bpy
    -0.57
    VersionUID
    -0.56
     @"/
    -0.54
     loisirs
    -0.54
    WaitGroup
    -0.54
     onPostExecute
    -0.54
     通販
    -0.54
    POSITIVE LOGITS
     points
    0.71
     bless
    0.66
     point
    0.62
     convicts
    0.59
     Points
    0.59
     تضيفلها
    0.58
    points
    0.57
     convict
    0.56
     convicted
    0.56
     Cause
    0.56
    Activations Density 0.000%

    No Known Activations