© 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. 38768
    Prev
    Next
    INDEX
    Explanations

    consistency

    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
    Consistent
    -1.00
     Consistent
    -0.98
    consistent
    -0.89
    eston
    -0.85
     consistent
    -0.83
     Freshwater
    -0.72
    ESTON
    -0.72
     olev
    -0.72
    XmlAccessorType
    -0.67
    ostante
    -0.65
    POSITIVE LOGITS
     censiti
    0.72
    ValueStyle
    0.70
     nonatomic
    0.60
     صوتيه
    0.59
    LikeLiked
    0.58
    nonatomic
    0.55
    dolu
    0.55
    Schedulers
    0.54
    Saludos
    0.53
      (
    0.53
    Activations Density 0.030%

    No Known Activations