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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74349
    Prev
    Next
    INDEX
    Explanations

    retinal

    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
    CharStream
    -0.72
     pinulongan
    -0.72
    jsdelivr
    -0.68
    cdnjs
    -0.65
     Celui
    -0.63
    jenigen
    -0.62
     Ceux
    -0.61
    minecraftforge
    -0.60
    !*\
    -0.57
     Those
    -0.56
    POSITIVE LOGITS
     the
    1.54
    private
    0.42
    the
    0.40
     éte
    0.40
    Czytaj
    0.39
    anschluss
    0.38
    Fonte
    0.37
    Ivoire
    0.36
    arbeid
    0.35
     giapp
    0.35
    Activations Density 0.000%

    No Known Activations