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. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12229
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns, words indicating thanks, and words indicating support

    oai_token-act-pair · gemini-2.0-flash

    Acknowledgements and contributions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_23/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
    دانشنامهٔ
    -0.67
    Diweddarwch
    -0.66
     beginnetje
    -0.58
     stanovnika
    -0.54
    thanx
    -0.52
    abestanden
    -0.51
     aussit
    -0.51
     despe
    -0.49
     camiset
    -0.49
     برانيه
    -0.49
    POSITIVE LOGITS
    Geplaatst
    0.79
     service
    0.59
    stringify
    0.56
    setVerticalGroup
    0.55
    VersionUID
    0.54
    InjectAttribute
    0.54
    AnimationsModule
    0.53
    جوايز
    0.53
     <<<<<<<<<<<<<<
    0.52
     show
    0.51
    Activations Density 1.951%

    No Known Activations