© 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. 0-CLT-HP
    7. 45521
    Prev
    Next
    INDEX
    Explanations

    NET

    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
    lgari
    -0.69
     TextStyle
    -0.57
    cheibe
    -0.57
     constexpr
    -0.54
    cheiben
    -0.53
    σθαι
    -0.52
    OGND
    -0.51
    ULER
    -0.50
    hesus
    -0.50
    ''',
    -0.50
    POSITIVE LOGITS
    MigrationBuilder
    0.89
    makeConstraints
    0.74
    awtextra
    0.69
    contentLoaded
    0.63
    DockStyle
    0.63
     NUKAT
    0.61
    e
    0.60
     doInBackground
    0.60
    PageContext
    0.57
    GOTREF
    0.57
    Activations Density 0.305%

    No Known Activations