© 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. 5-CLT-HP
    7. 2185
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    >>();
    -0.49
    disciplinary
    -0.41
    endphp
    -0.40
     Generous
    -0.39
     Formal
    -0.39
    __((
    -0.39
     comunit
    -0.38
    くれます
    -0.38
    ]-'
    -0.38
     Otherwise
    -0.37
    POSITIVE LOGITS
     محفوظة
    0.73
    fjspx
    0.70
    קישורים
    0.65
    StoryboardSegue
    0.62
    twimg
    0.60
    Rüyada
    0.59
     cliquer
    0.58
     calendriers
    0.57
     désolés
    0.57
     ivelany
    0.56
    Activations Density 0.006%

    No Known Activations