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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5907
    Prev
    Next
    INDEX
    Explanations

    the first few characters of the username "Ankman" in a chat log

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'An'

    np_token-act-pair-logits · gpt-4o-mini

    An

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
     transfieras
    -0.69
    mergeFrom
    -0.65
    verifyException
    -0.64
     censiti
    -0.62
     defaultstate
    -0.61
    ValueStyle
    -0.61
    IVEREF
    -0.61
     مؤرشف
    -0.61
     JADX
    -0.61
     nakalista
    -0.59
    POSITIVE LOGITS
     cheminée
    0.47
     occaf
    0.46
     eſ
    0.46
     extension
    0.45
     obſ
    0.44
     AdapterView
    0.44
     préfère
    0.44
     colère
    0.44
     silenzio
    0.43
     experiment
    0.43
    Activations Density 1.084%

    No Known Activations