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. 16375
    Prev
    Next
    INDEX
    Explanations

    a variety of different patterns

    oai_token-act-pair · gemini-2.0-flash

    therapy

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

    clothing

    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
     zelf
    -1.11
     self
    -1.09
     tự
    -1.03
    selbst
    -0.98
     selbst
    -0.98
     samodziel
    -0.96
     самостоятельно
    -0.96
     independently
    -0.95
     Self
    -0.94
     самостоя
    -0.92
    POSITIVE LOGITS
    ByVersion
    0.52
    msgTypes
    0.51
    показания
    0.47
    ilever
    0.44
    addGroup
    0.43
     fertili
    0.42
    Denomin
    0.42
     consular
    0.42
    paramMap
    0.42
     smoke
    0.42
    Activations Density 2.342%

    No Known Activations