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. 14182
    Prev
    Next
    INDEX
    Explanations

    the preposition "with," but also other short prepositions

    oai_token-act-pair · gemini-2.0-flash

    archaic words

    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
    pective
    -0.48
     brazos
    -0.48
     quanto
    -0.47
    AndPassword
    -0.47
     sí
    -0.47
     das
    -0.47
    ิ่ง
    -0.46
     l
    -0.45
    SPECIFIED
    -0.44
     
    -0.43
    POSITIVE LOGITS
     houſe
    0.93
     Monfieur
    0.91
     Diſ
    0.90
     itſelf
    0.88
     Houſe
    0.88
     raiſ
    0.88
     Reſ
    0.88
     Theſe
    0.88
     Anſ
    0.86
     pleaſure
    0.86
    Activations Density 1.632%

    No Known Activations