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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2317
    Prev
    Next
    INDEX
    Explanations

    the start of certain words beginning with the letters "po"

    oai_token-act-pair · gemini-2.0-flash

    Words starting 'po'

    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
    تقاوى
    -0.67
     mdi
    -0.67
    __*/
    -0.62
    Personensuche
    -0.62
    Tikang
    -0.60
    netbeans
    -0.59
    endpush
    -0.59
    complexContent
    -0.58
    hassee
    -0.57
     muualla
    -0.57
    POSITIVE LOGITS
    ITED
    0.56
    taje
    0.49
    izy
    0.48
    gnes
    0.47
    jspx
    0.46
    sibility
    0.46
     onCreateView
    0.46
    celess
    0.45
    ITOS
    0.45
    ciences
    0.45
    Activations Density 4.479%

    No Known Activations