© 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. 92043
    Prev
    Next
    INDEX
    Explanations

    parts

    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
     căr
    -0.50
    ,
    -0.42
     måned
    -0.42
     grå
    -0.41
    wany
    -0.39
     mør
    -0.39
     trás
    -0.39
     vías
    -0.39
    argb
    -0.39
     voix
    -0.39
    POSITIVE LOGITS
    ChildScrollView
    0.69
    PyExc
    0.68
     defaultstate
    0.67
    Izvori
    0.63
     tartalomajánló
    0.63
     cref
    0.62
    ReusableCell
    0.62
    脚注の使い方
    0.60
    (;;)
    0.60
    หมือน
    0.59
    Activations Density 0.001%

    No Known Activations