© 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. 92199
    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
    而已
    -0.47
    setColumns
    -0.44
     or
    -0.41
     course
    -0.41
    schild
    -0.40
     message
    -0.40
    phite
    -0.40
    ience
    -0.39
    æder
    -0.38
    idoscope
    -0.37
    POSITIVE LOGITS
    AsUp
    0.87
    Personendaten
    0.65
    migrationBuilder
    0.64
    хьтан
    0.63
     thiệu
    0.59
    脚注の使い方
    0.56
    Бахар
    0.56
     snippetHide
    0.56
    CodeAttribute
    0.54
    fraction
    0.54
    Activations Density 0.005%

    No Known Activations