© 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. 4-CLT-HP
    7. 229
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    extAlignment
    -0.60
    oneofs
    -0.60
    tamol
    -0.59
     nonatomic
    -0.59
     الحره
    -0.58
    okus
    -0.57
    省市镇
    -0.56
    bonucle
    -0.54
    期刊论文
    -0.54
    multer
    -0.54
    POSITIVE LOGITS
     has
    0.71
     have
    0.63
    Has
    0.56
    has
    0.56
     betweenstory
    0.53
    ellón
    0.50
     CONCLUSIONS
    0.49
     Have
    0.49
     conclusion
    0.49
    <bos>
    0.49
    Activations Density 0.007%

    No Known Activations