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. 11045
    Prev
    Next
    INDEX
    Explanations

    text related to the Android operating system and software development

    oai_token-act-pair · gemini-2.0-flash

    terms related to Android application installation and development

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

    android

    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
    StructEnd
    -0.77
    KommentareTeilen
    -0.70
    Życiorys
    -0.69
    ArgsConstructor
    -0.66
    stateProvider
    -0.63
    AutoScale
    -0.62
     nakalista
    -0.61
    enumi
    -0.60
     يتيمه
    -0.59
    styleType
    -0.58
    POSITIVE LOGITS
     perio
    0.45
    enge
    0.43
    perio
    0.42
    link
    0.41
     cré
    0.41
    eng
    0.41
    Portail
    0.40
    monde
    0.40
     jie
    0.39
     sufficient
    0.38
    Activations Density 1.382%

    No Known Activations