Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16266
    Prev
    Next
    INDEX
    Explanations

    proper nouns or descriptors of geographical markers and people's names

    oai_token-act-pair · gemini-2.0-flash

    network

    np_token-act-pair-logits · gemini-2.0-flash

    National Network

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     useDispatch
    -0.56
     تانيه
    -0.55
     Schilder
    -0.55
    })();
    
    -0.55
    isFull
    -0.53
     kiệm
    -0.52
     الحره
    -0.52
    '])){
    
    -0.51
    "]];
    -0.50
    ợp
    -0.50
    POSITIVE LOGITS
     National
    0.75
     Network
    0.68
    National
    0.65
     network
    0.65
     Networks
    0.65
    Network
    0.64
     n
    0.63
     Nationals
    0.62
     ne
    0.61
     national
    0.60
    Activations Density 0.617%

    No Known Activations