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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1663
    Prev
    Next
    INDEX
    Explanations

    the subject of veterinary medicine and animal care

    oai_token-act-pair · gemini-2.0-flash

    veterinary medicine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     animal
    -1.93
     Animal
    -1.87
    Animal
    -1.74
    animal
    -1.73
     ANIMAL
    -1.71
     pet
    -1.68
     animals
    -1.66
     Animals
    -1.60
     veterinary
    -1.57
    ANIMAL
    -1.57
    POSITIVE LOGITS
    rungsseite
    0.59
    reactivex
    0.51
    MeasureSpec
    0.47
    kelen
    0.47
    phite
    0.46
    YLON
    0.46
    bootstrapcdn
    0.45
     createSlice
    0.45
     الحره
    0.45
    Dział
    0.44
    Activations Density 1.292%

    No Known Activations