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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73738
    Prev
    Next
    INDEX
    Explanations

    "ab"

    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
    RTEE
    -0.59
     bicchiere
    -0.58
     Upan
    -0.54
    йся
    -0.51
     CommandType
    -0.51
    occasione
    -0.50
     pia
    -0.50
     StatefulWidget
    -0.50
    etra
    -0.49
     Cater
    -0.48
    POSITIVE LOGITS
    original
    0.73
    elemField
    0.66
     original
    0.62
    ORIGINAL
    0.59
    domen
    0.59
    orig
    0.59
    NameInMap
    0.54
     صوتيه
    0.52
    origin
    0.52
    ortion
    0.52
    Activations Density 0.003%

    No Known Activations