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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16260
    Prev
    Next
    INDEX
    Explanations

    android code configurations

    oai_token-act-pair · gemini-2.0-flash

    Computer 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
    expandindo
    -1.08
     виправивши
    -0.91
    存于互联网档案馆
    -0.89
     myſelf
    -0.88
     themſelves
    -0.85
    UrlResolution
    -0.84
     himſelf
    -0.78
    LookAnd
    -0.77
     IBOutlet
    -0.77
     reaſon
    -0.77
    POSITIVE LOGITS
    Label
    0.42
     Schie
    0.41
     पै
    0.41
     cha
    0.40
     ord
    0.40
    censored
    0.40
    bia
    0.39
     top
    0.39
    斤
    0.38
     P
    0.38
    Activations Density 0.927%

    No Known Activations