© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15884
    Prev
    Next
    INDEX
    Explanations

    locations/names

    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
     propOrder
    -0.67
    UnsafeEnabled
    -0.67
     ErrIntOverflow
    -0.64
     poussière
    -0.61
     betweenstory
    -0.60
    AutoresizingMask
    -0.60
    RenderAtEndOf
    -0.60
    bootstrapcdn
    -0.59
    ˏ
    -0.58
    UseVisualStyle
    -0.58
    POSITIVE LOGITS
     NKC
    0.48
    lccn
    0.43
     ratific
    0.41
    /*!
    0.41
    ness
    0.41
    OPSIS
    0.41
     <<<<<<<<<<<<<<
    0.40
     lla
    0.40
    Satis
    0.39
     vhs
    0.39
    Activations Density 0.008%

    No Known Activations