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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1544
    Prev
    Next
    INDEX
    Explanations

    code snippets or legal jargon that refer to pre-existing conditions or file existence

    oai_token-act-pair · gemini-2.0-flash

    Discussing existence or contracts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     exist
    -2.72
     exists
    -2.59
     existed
    -2.42
     EXIST
    -2.34
     existence
    -2.34
    exist
    -2.33
     Exists
    -2.23
     Existing
    -2.20
    EXIST
    -2.17
     Exist
    -2.16
    POSITIVE LOGITS
    出版年
    0.65
    prus
    0.55
    eqn
    0.51
    脚注の使い方
    0.50
    MENAFN
    0.49
    bootstrapcdn
    0.48
     useParams
    0.48
    OutputType
    0.47
     ankles
    0.47
    "?>
    0.46
    Activations Density 2.599%

    No Known Activations