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. 74396
    Prev
    Next
    INDEX
    Explanations

    Foreign language phrases

    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
    \{\\
    -0.86
     ModelExpression
    -0.80
    Autoritní
    -0.69
     ArrayAdapter
    -0.65
    windowFixed
    -0.64
    IVEREF
    -0.63
    HasBeenSet
    -0.61
     Walkover
    -0.61
    onViewCreated
    -0.60
    ]='\
    -0.59
    POSITIVE LOGITS
    DE
    0.53
    DataAnnotations
    0.52
     تضيفلها
    0.47
    del
    0.44
     proposer
    0.42
     popoli
    0.41
    Logan
    0.40
     emel
    0.40
    ليه
    0.40
     précision
    0.40
    Activations Density 0.011%

    No Known Activations