© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74546
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     تضيفلها
    -0.65
     InputDecoration
    -0.64
     épis
    -0.62
     himſelf
    -0.62
    -------------</
    -0.60
     ſhall
    -0.59
     itſelf
    -0.59
     Penelitian
    -0.58
    aarrggbb
    -0.57
     refroid
    -0.57
    POSITIVE LOGITS
    expandindo
    0.57
    oneg
    0.52
     journey
    0.46
     timeline
    0.45
     file
    0.44
     programme
    0.43
     register
    0.42
     dictionary
    0.42
     ode
    0.40
    iscope
    0.40
    Activations Density 0.002%

    No Known Activations