© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1002
    Prev
    Next
    INDEX
    Explanations

    certainty, prevalence

    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
     definitely
    -1.55
     certainly
    -1.38
     sicuramente
    -1.35
    definitely
    -1.32
    certainly
    -1.30
     Definitely
    -1.25
     certamente
    -1.23
    Definitely
    -1.23
     ciertamente
    -1.15
     Certainly
    -1.08
    POSITIVE LOGITS
    ly
    0.71
     ung
    0.59
    ally
    0.54
     source
    0.50
     law
    0.50
    InvalidProtocol
    0.49
     gain
    0.49
     powers
    0.48
     uses
    0.48
    LY
    0.48
    Activations Density 0.038%

    No Known Activations