Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39133
    Prev
    Next
    INDEX
    Explanations

    legal or technical texts

    np_max-act · 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
    quelles
    -0.63
    WithIOException
    -0.60
    Atsauces
    -0.60
     profondità
    -0.57
    исленность
    -0.53
     ExecuteAsync
    -0.51
    Vaata
    -0.51
    ization
    -0.50
    udesta
    -0.50
    böz
    -0.49
    POSITIVE LOGITS
    TagHelper
    0.60
    omitempty
    0.56
    RenderAtEndOf
    0.55
    InteropServices
    0.53
    PYX
    0.53
     استنادى
    0.52
    etermined
    0.51
     CanadaChoose
    0.50
    °•
    0.50
     setuptools
    0.50
    Activations Density 0.221%

    No Known Activations