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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14210
    Prev
    Next
    INDEX
    Explanations

    words relating to criminal charges

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
     synthesis
    -0.59
     timely
    -0.59
     synt
    -0.56
     synthe
    -0.51
    合成
    -0.49
     surrounded
    -0.48
     wrote
    -0.45
     regia
    -0.45
     Synthesis
    -0.45
    й
    -0.45
    POSITIVE LOGITS
    ThroughAttribute
    1.04
     MainAxisSize
    1.01
    AddTagHelper
    0.99
    WireFormatLite
    0.95
     Roskov
    0.94
    StructEnd
    0.94
    SharedDtor
    0.94
     doInBackground
    0.94
     FontWeight
    0.94
    WriteTagHelper
    0.92
    Activations Density 3.342%

    No Known Activations