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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11008
    Prev
    Next
    INDEX
    Explanations

    words referring to renting or leasing property

    oai_token-act-pair · gemini-2.0-flash

    specific code or technical terms

    np_token-act-pair-logits · gpt-4o-mini

    rent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    racite
    -0.52
     AttributeSet
    -0.48
    Чита
    -0.44
     blat
    -0.44
     slate
    -0.43
    assertArray
    -0.43
     Чита
    -0.42
    mistak
    -0.41
    restrial
    -0.40
     PrintWriter
    -0.40
    POSITIVE LOGITS
     ويكيپيديا
    0.73
    AddTagHelper
    0.69
     initComponents
    0.66
    cshtml
    0.64
    Rhestr
    0.63
     Chwiliwch
    0.60
     ProtoMessage
    0.59
    NameInMap
    0.59
    Архівовано
    0.59
    Datuak
    0.57
    Activations Density 3.661%

    No Known Activations