© 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. 1-CLT-HP
    4. 563
    Prev
    Next
    INDEX
    Explanations

    Nation

    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
     ProtoMessage
    -0.69
    ReusableCell
    -0.66
     استنادى
    -0.60
     vostri
    -0.57
     للاسماء
    -0.49
    amaño
    -0.49
     démocr
    -0.48
     الحره
    -0.48
    LLocation
    -0.48
     Grecs
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.73
    tahui
    0.70
    izr
    0.60
    consistent
    0.57
    NEL
    0.54
     consistent
    0.54
    z
    0.54
    umoj
    0.53
     enrolled
    0.53
     Consistent
    0.53
    Activations Density 0.010%

    No Known Activations