© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1398
    Prev
    Next
    INDEX
    Explanations

    consist

    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
     consist
    -1.06
     consists
    -0.78
     consisted
    -0.76
    sterious
    -0.73
    certified
    -0.70
     officially
    -0.69
     qualified
    -0.68
     certified
    -0.68
    @[+][
    -0.67
     portion
    -0.66
    POSITIVE LOGITS
     of
    0.74
    IonicModule
    0.54
    ècie
    0.52
     Of
    0.49
    mockito
    0.47
    tvguidetime
    0.47
    Of
    0.47
     neither
    0.47
    Locus
    0.47
     linkovi
    0.47
    Activations Density 0.077%

    No Known Activations