© 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. 1-CLT-HP
    7. 45918
    Prev
    Next
    INDEX
    Explanations

    calibre and misspellings

    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
     Cali
    -0.88
    Cali
    -0.77
    Personendaten
    -0.73
    WillAppear
    -0.56
    cali
    -0.56
    styleType
    -0.55
     cali
    -0.49
    CodedInputStream
    -0.49
    AndroidJUnit
    -0.49
    corer
    -0.48
    POSITIVE LOGITS
    ber
    0.73
    phs
    0.69
    bre
    0.67
    ph
    0.66
    phal
    0.65
    Raised
    0.59
     Raised
    0.57
    raised
    0.56
    fer
    0.56
    φορ
    0.55
    Activations Density 0.009%

    No Known Activations