© 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. 0-CLT-HP
    7. 1232
    Prev
    Next
    INDEX
    Explanations

    level

    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
     level
    -1.45
    level
    -1.17
     nivel
    -1.00
     levels
    -0.99
     nível
    -0.99
     LEVEL
    -0.96
    Level
    -0.95
     niveau
    -0.92
     livello
    -0.90
    LEVEL
    -0.90
    POSITIVE LOGITS
     patterning
    0.56
     of
    0.55
     متعلقه
    0.55
     adsorbed
    0.55
    jaros
    0.54
     autocorrelation
    0.53
     diffusivity
    0.52
     Uncertainty
    0.52
    μμ
    0.52
    Access
    0.52
    Activations Density 0.032%

    No Known Activations