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. 14005
    Prev
    Next
    INDEX
    Explanations

    terms related to programming languages and data structures.

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    findpost
    -0.64
    Clik
    -0.62
     saites
    -0.56
     schla
    -0.52
    createServer
    -0.51
     femmin
    -0.50
    //});
    -0.48
    httphttps
    -0.48
     gratuitamente
    -0.47
    ⓘ
    -0.47
    POSITIVE LOGITS
    ]='\
    0.65
    ignty
    0.62
    polation
    0.55
     calldata
    0.54
    uesday
    0.53
    digm
    0.52
    ueira
    0.51
    CastException
    0.50
    gration
    0.49
    ximately
    0.49
    Activations Density 5.797%

    No Known Activations