© 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. 0-CLT-HP
    7. 45240
    Prev
    Next
    INDEX
    Explanations

    BMP

    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
    lic
    -0.56
     segmented
    -0.54
    dias
    -0.53
    inea
    -0.52
    abo
    -0.49
    land
    -0.49
    XML
    -0.48
    estre
    -0.48
     share
    -0.47
    dahl
    -0.47
    POSITIVE LOGITS
     betweenstory
    1.03
    AndEndTag
    0.98
     متعلقه
    0.93
     propOrder
    0.85
     autorytatywna
    0.84
     '\\;'
    0.82
     pinulongan
    0.78
    
    0.76
     itſelf
    0.76
    TagMode
    0.75
    Activations Density 0.185%

    No Known Activations