© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 78150
    Prev
    Next
    INDEX
    Explanations

    Beginning of Topics

    np_max-act-logits · 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
    Negative Logits
    )」
    -1.40
    ),”
    -1.34
    ])))
    -1.30
    ”)
    -1.27
    )”
    -1.23
    '])
    -1.22
    ']);
    
    -1.22
    </h6>
    -1.20
    '])
    
    -1.20
    ]))
    
    -1.20
    POSITIVE LOGITS
    fony
    0.57
    AlterField
    0.55
    ."
    0.52
    principalColumn
    0.49
    Географи
    0.49
    awtextra
    0.48
    isSuccessful
    0.48
    Ở
    0.47
    PMailer
    0.47
    msgSender
    0.46
    Activations Density 0.117%

    No Known Activations