© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 442
    Prev
    Next
    INDEX
    Explanations

    atmosphere

    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
     atmosphere
    -0.74
    atmosphere
    -0.69
     atmospheres
    -0.64
    oya
    -0.60
    avy
    -0.50
     ::=
    -0.50
     atmosfera
    -0.49
    atmos
    -0.49
    ]:
    -0.47
    Aktualisiert
    -0.47
    POSITIVE LOGITS
    oa̍t
    0.72
    Зноскі
    0.62
    MLLoader
    0.60
    βολ
    0.60
    WebElementEntity
    0.56
     שוליים
    0.56
    devamını
    0.56
    DotNetBar
    0.55
     typelib
    0.55
    ness
    0.54
    Activations Density 0.012%

    No Known Activations