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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73965
    Prev
    Next
    INDEX
    Explanations

    col

    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
     mer
    -0.54
     Meri
    -0.54
    imer
    -0.53
    tib
    -0.52
     Mer
    -0.52
    interopRequire
    -0.52
     MERR
    -0.52
    Mer
    -0.48
    tyg
    -0.48
     cytos
    -0.47
    POSITIVE LOGITS
     nakalista
    0.62
    ScopeManager
    0.56
    发表于
    0.55
    SharedCtor
    0.54
    Personensuche
    0.52
     revés
    0.51
    OptionsMenu
    0.49
    MemoryWarning
    0.49
    origen
    0.47
    expandindo
    0.47
    Activations Density 0.004%

    No Known Activations