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. 14189
    Prev
    Next
    INDEX
    Explanations

    negative sentiment about communicating information

    oai_token-act-pair · gemini-2.0-flash

    Refusing to comment

    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
    rrggbb
    -0.76
    expandindo
    -0.71
    PyExc
    -0.70
     الحره
    -0.67
    بوابة
    -0.67
     Wikimedijinoj
    -0.66
    oredCriteria
    -0.66
    }$​
    -0.65
    didSet
    -0.64
    Autoritní
    -0.63
    POSITIVE LOGITS
    comment
    0.50
     Comment
    0.48
    withIdentifier
    0.47
     comment
    0.46
     easy
    0.45
    Comment
    0.44
     known
    0.43
    WithIdentifier
    0.42
     BorderRadius
    0.42
    itinéraire
    0.42
    Activations Density 0.922%

    No Known Activations