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. 22-CLT-HP
    4. 74433
    Prev
    Next
    INDEX
    Explanations

    named entities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fieldNum
    -0.66
     kaynağından
    -0.60
     nahilalakip
    -0.59
     disambiguazione
    -0.57
    KommentareTeilen
    -0.57
    LookAnd
    -0.56
    featureID
    -0.56
     насељу
    -0.56
    Printable
    -0.55
    FieldBuilder
    -0.52
    POSITIVE LOGITS
    INCREF
    0.55
    ToDecimal
    0.49
     سكانية
    0.49
     Chomsky
    0.48
     castor
    0.48
    brando
    0.48
    omiast
    0.47
     cân
    0.47
    ChildScrollView
    0.47
    ppler
    0.47
    Activations Density 0.001%

    No Known Activations