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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14144
    Prev
    Next
    INDEX
    Explanations

    the word "abandonment" and related forms

    oai_token-act-pair · gemini-2.0-flash

    ment

    np_max-act · 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
    úč
    -0.49
     Rät
    -0.49
     vägen
    -0.47
    zeugen
    -0.47
     souverain
    -0.47
     Analog
    -0.46
    survi
    -0.46
     Oncology
    -0.45
    ENCOD
    -0.45
    Analog
    -0.44
    POSITIVE LOGITS
    WriteBarrier
    0.90
    MessageOf
    0.87
    DispatchToProps
    0.85
    ThroughAttribute
    0.85
    NameInMap
    0.82
     ExecuteAsync
    0.82
    脚注の使い方
    0.80
     &___
    0.79
    PreferredItem
    0.78
    MigrationBuilder
    0.78
    Activations Density 0.456%

    No Known Activations