© 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. 5-CLT-HP
    7. 2312
    Prev
    Next
    INDEX
    Explanations

    (

    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
    ConstraintMaker
    -0.68
    دانشنامهٔ
    -0.63
    μως
    -0.61
     ويكيپيديا
    -0.59
    TagMode
    -0.58
     Pacer
    -0.57
    AndEndTag
    -0.57
     invokingState
    -0.57
    цездатний
    -0.56
     MainAxisSize
    -0.56
    POSITIVE LOGITS
    rande
    0.48
     ORIG
    0.45
    Ordinal
    0.44
    NSIndexPath
    0.44
     שוליים
    0.44
    SDG
    0.43
    Origin
    0.43
    dia
    0.43
    Cocoa
    0.43
    selectedIndex
    0.43
    Activations Density 0.005%

    No Known Activations