© 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. 20-CLT-HP
    4. 74571
    Prev
    Next
    INDEX
    Explanations

    time units

    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
     picioare
    -0.83
     ainfi
    -0.80
     tranſ
    -0.79
     obſ
    -0.79
     étoient
    -0.77
     avoient
    -0.75
     plufieurs
    -0.72
     pouvoit
    -0.70
     paſſ
    -0.70
    SourceChecksum
    -0.70
    POSITIVE LOGITS
     weeks
    0.56
     months
    0.54
     days
    0.54
     year
    0.52
    -
    0.52
     
    0.49
     years
    0.48
     Weeks
    0.46
    esgue
    0.43
    1
    0.40
    Activations Density 0.009%

    No Known Activations