Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14043
    Prev
    Next
    INDEX
    Explanations

    descriptions of rear-facing features in cars

    oai_token-act-pair · gemini-2.0-flash

    tail/rear

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     front
    -0.72
    Front
    -0.64
    front
    -0.64
     head
    -0.61
     Front
    -0.60
     FRONT
    -0.59
     frente
    -0.58
    Head
    -0.58
    head
    -0.57
     fronts
    -0.57
    POSITIVE LOGITS
    verwijspagina
    0.75
     CreateTagHelper
    0.69
    الدراسه
    0.64
     ta
    0.63
    peutic
    0.60
    ifflin
    0.58
     estekak
    0.58
    homonymie
    0.56
     tail
    0.55
    تقاوى
    0.54
    Activations Density 1.045%

    No Known Activations