© 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. 5-CLT-HP
    7. 3401
    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
    <bos>
    -0.49
    出版年
    -0.48
    ოლი
    -0.47
    MLLoader
    -0.46
    日閲覧
    -0.46
     yesterday
    -0.46
    apunov
    -0.46
    AutoScaleMode
    -0.46
     Outbreak
    -0.44
     tickets
    -0.43
    POSITIVE LOGITS
    sidemargin
    0.49
    <?
    0.45
    tuous
    0.43
     &___
    0.43
    awtextra
    0.42
    ,:),
    0.41
    databinding
    0.40
    rmızı
    0.40
    ^{+}\
    0.39
     kasarigan
    0.38
    Activations Density 0.007%

    No Known Activations