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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14110
    Prev
    Next
    INDEX
    Explanations

    bracketed citation numbers within texts

    oai_token-act-pair · gemini-2.0-flash

    say number 8

    np_max-act-logits · gemini-2.0-flash

    citation numbers and reference identifiers in academic papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @johnny
    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
     of
    -0.56
     
    -0.51
     V
    -0.47
     der
    -0.45
     U
    -0.45
    3
    -0.45
     T
    -0.45
     t
    -0.44
     cre
    -0.44
     quy
    -0.44
    POSITIVE LOGITS
     Efq
    1.14
    RenderAtEndOf
    1.12
     itſelf
    1.06
     myſelf
    1.05
     Majefty
    1.04
    
    1.02
    windowFixed
    1.00
     doubtnut
    0.98
     houſe
    0.98
    AutoScaleMode
    0.98
    Activations Density 4.610%

    No Known Activations