© 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. 43632
    Prev
    Next
    INDEX
    Explanations

    Although

    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
     Wants
    -0.63
    A
    -0.63
     Continues
    -0.62
     Attempt
    -0.61
     flèche
    -0.60
     Want
    -0.60
     Needs
    -0.60
     Behind
    -0.60
     Would
    -0.59
     Points
    -0.59
    POSITIVE LOGITS
     незавершена
    0.69
    <bos>
    0.68
     Савезне
    0.67
     the
    0.58
    évaluateur
    0.58
     I
    0.57
     समीक्षक
    0.57
     betweenstory
    0.51
    مدينة
    0.51
     he
    0.50
    Activations Density 0.045%

    No Known Activations