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. 20-CLT-HP
    4. 74056
    Prev
    Next
    INDEX
    Explanations

    rubber

    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
    Jereo
    -0.76
    BagConstraints
    -0.74
    DockStyle
    -0.70
    JsonKey
    -0.65
     BoxFit
    -0.63
     lèvres
    -0.60
     ongles
    -0.59
     OFDb
    -0.59
    tonsoft
    -0.58
     незавершена
    -0.58
    POSITIVE LOGITS
     arms
    0.52
     over
    0.50
     lenker
    0.49
     headband
    0.47
    protoimpl
    0.46
     cups
    0.45
    hdessä
    0.45
     spacy
    0.45
    ⓧ
    0.44
     copas
    0.43
    Activations Density 0.001%

    No Known Activations