© 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. 1-CLT-HP
    7. 15841
    Prev
    Next
    INDEX
    Explanations

    ass

    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
    sizeCache
    -0.86
    Източници
    -0.77
     propOrder
    -0.76
    ResumeLayout
    -0.73
     дописавши
    -0.72
    WriteLiteral
    -0.71
    SuspendLayout
    -0.69
    Джерела
    -0.68
    offsetof
    -0.68
    oa̍t
    -0.67
    POSITIVE LOGITS
     autorytatywna
    0.41
    $$\
    0.36
    minator
    0.35
    ">@
    0.35
    PullParser
    0.35
     rivales
    0.34
    ito
    0.34
    imal
    0.34
     Greyhound
    0.34
     wikipagina
    0.33
    Activations Density 0.078%

    No Known Activations