© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1168
    Prev
    Next
    INDEX
    Explanations

    Training and benefits

    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
    ning
    -0.63
    nings
    -0.58
    tish
    -0.57
    machi
    -0.56
    ener
    -0.54
     ferons
    -0.54
    tings
    -0.52
    ception
    -0.51
    eners
    -0.51
    __":
    
    -0.50
    POSITIVE LOGITS
     дописавши
    0.63
    TagMode
    0.61
    تقاوى
    0.59
    الحياه
    0.59
     ModelExpression
    0.58
    MessageOf
    0.58
     indisponible
    0.57
     surla
    0.57
    ValueStyle
    0.56
    
    0.56
    Activations Density 0.027%

    No Known Activations