© 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. 41626
    Prev
    Next
    INDEX
    Explanations

    Articles and stories

    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
    marked
    -0.50
    matic
    -0.48
    ra
    -0.48
    sp
    -0.48
     sea
    -0.47
    RA
    -0.47
     island
    -0.46
     mass
    -0.46
     for
    -0.46
    ref
    -0.46
    POSITIVE LOGITS
     betweenstory
    1.06
    principalTable
    1.00
     '\\;'
    0.84
    httphttps
    0.84
     disambiguazione
    0.81
    Бахар
    0.79
    WebElementEntity
    0.79
    最快更新
    0.78
    Personendaten
    0.78
    Vidite
    0.77
    Activations Density 0.069%

    No Known Activations