© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41294
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    脚注の使い方
    -0.74
    لينكات
    -0.72
    invokeLater
    -0.68
    SequentialGroup
    -0.67
    новниш
    -0.67
    клопе
    -0.67
     tartalomajánló
    -0.66
     málaga
    -0.65
    argout
    -0.65
    hes
    -0.65
    POSITIVE LOGITS
    a
    0.55
    e
    0.53
     products
    0.49
     Fora
    0.49
     terem
    0.47
    прави
    0.45
    worldwide
    0.45
     chất
    0.45
    education
    0.45
    setIsLoading
    0.44
    Activations Density 0.139%

    No Known Activations