© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 50
    Prev
    Next
    INDEX
    Explanations

    right

    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
     שוליים
    -0.60
    XmlAccessType
    -0.56
    LEncoder
    -0.49
    apunov
    -0.49
    рг
    -0.47
    ILayout
    -0.46
    MOUTH
    -0.45
    VersionUID
    -0.45
    por
    -0.45
    tel
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.76
     lenker
    0.65
    AndEndTag
    0.62
     kasarigan
    0.59
    цездатний
    0.58
     Ooster
    0.57
     MenuView
    0.57
     AspNetCore
    0.57
    IsMutable
    0.56
     autorytatywna
    0.56
    Activations Density 0.036%

    No Known Activations