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. 11134
    Prev
    Next
    INDEX
    Explanations

    the beginning of the word "constitutional" or other words starting with "cons"

    oai_token-act-pair · gemini-2.0-flash

    terms related to 'cons' or consolidation

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

    cons

    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
    ForValue
    -0.43
    kuuta
    -0.43
    shub
    -0.42
    Acc
    -0.42
    Ab
    -0.41
    bbi
    -0.39
    vila
    -0.37
    IBarButtonItem
    -0.36
    entiary
    -0.36
     PLWABN
    -0.36
    POSITIVE LOGITS
    出版年
    0.75
     JpaRepository
    0.71
    migrationBuilder
    0.71
    IsMutable
    0.68
    ruptedException
    0.66
    rrggbb
    0.65
    WithIOException
    0.62
    GEBURTSDATUM
    0.61
     viewType
    0.60
     päät
    0.60
    Activations Density 0.289%

    No Known Activations