© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92443
    Prev
    Next
    INDEX
    Explanations

    usage

    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
     Usage
    -1.16
     تانيه
    -1.13
     uſe
    -1.07
    ſelf
    -1.06
    ſelves
    -1.04
     Utilisation
    -1.02
    usage
    -1.01
     usage
    -1.00
     consumption
    -0.98
    Consumption
    -0.98
    POSITIVE LOGITS
     of
    1.21
     and
    0.70
     from
    0.69
     by
    0.68
     to
    0.66
    ,
    0.65
     in
    0.63
     for
    0.60
     (
    0.59
     process
    0.59
    Activations Density 0.101%

    No Known Activations