© 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. 5-CLT-HP
    7. 5912
    Prev
    Next
    INDEX
    Explanations

    vague quantifiers

    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
     defaultstate
    -0.81
     AttributeSet
    -0.77
     kasarigan
    -0.76
    UrlResolution
    -0.75
     lenker
    -0.75
    SharedCtor
    -0.74
     فريبيس
    -0.73
     NSCoder
    -0.72
    PyExc
    -0.71
     незавершена
    -0.68
    POSITIVE LOGITS
    TAINER
    0.48
     виправивши
    0.48
     either
    0.47
    بسم
    0.47
    vaiz
    0.47
    nsan
    0.44
     sure
    0.44
     større
    0.44
     knowing
    0.42
     سواء
    0.42
    Activations Density 0.005%

    No Known Activations