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. 16353
    Prev
    Next
    INDEX
    Explanations

    mentions of money changing hands over time-related deals, especially with the word "over".

    oai_token-act-pair · gemini-2.0-flash

    mixed case tokens

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

    ve

    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
     beginnetje
    -0.66
     InputDecoration
    -0.57
    UserScript
    -0.52
    VolleyError
    -0.50
    Viitteet
    -0.49
     Wiktionnaire
    -0.49
    rikes
    -0.49
     onCancelled
    -0.49
    kháu
    -0.49
    labelControl
    -0.49
    POSITIVE LOGITS
    IsMutable
    0.52
     cabezas
    0.49
    IZO
    0.47
     couverts
    0.46
    ENGTH
    0.46
     greu
    0.46
     piratas
    0.46
     externi
    0.45
    izo
    0.45
    esto
    0.44
    Activations Density 2.552%

    No Known Activations