© 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. 45826
    Prev
    Next
    INDEX
    Explanations

    thermal

    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
     CreateTagHelper
    -0.72
    TypedDataSet
    -0.60
     ennemi
    -0.59
    marcos
    -0.56
    destroyAll
    -0.55
     тё
    -0.55
     Thermal
    -0.53
    ^(@
    -0.53
    Modelling
    -0.53
     warm
    -0.52
    POSITIVE LOGITS
     Alembic
    0.53
    Gemeinden
    0.52
    ▼
    0.52
    niu
    0.50
    Beck
    0.49
    CV
    0.48
    BCS
    0.47
    CDT
    0.47
     colspan
    0.46
     chut
    0.45
    Activations Density 0.373%

    No Known Activations