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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45577
    Prev
    Next
    INDEX
    Explanations

    vision

    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
    
    -1.05
     vision
    -0.83
     تانيه
    -0.74
     consultato
    -0.69
    vision
    -0.67
     postIndex
    -0.61
     NSCoder
    -0.61
     Vision
    -0.60
     createSprite
    -0.60
    consulté
    -0.59
    POSITIVE LOGITS
     of
    0.89
     for
    0.61
     algorithm
    0.56
    ing
    0.55
    ed
    0.54
    ising
    0.54
     Heilig
    0.54
     statement
    0.52
     implemented
    0.52
    力を
    0.52
    Activations Density 0.026%

    No Known Activations