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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10158
    Prev
    Next
    INDEX
    Explanations

    mentions of cookie policies on websites

    oai_token-act-pair · gemini-2.0-flash

    Website cookie policies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_19/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
     المعيارى
    -0.80
    PerformLayout
    -0.78
    principalColumn
    -0.76
    Geplaatst
    -0.75
    ThroughAttribute
    -0.74
    mybatisplus
    -0.74
    msgSender
    -0.74
     Paglinawan
    -0.72
    Tembelea
    -0.72
    </thead>
    -0.71
    POSITIVE LOGITS
     numerus
    0.40
     autorisé
    0.39
     bianchi
    0.39
     automated
    0.37
     sp
    0.37
     affitto
    0.36
     automation
    0.36
     inteligentes
    0.36
     assurance
    0.35
    spring
    0.35
    Activations Density 3.850%

    No Known Activations