© 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. 5-CLT-HP
    7. 92204
    Prev
    Next
    INDEX
    Explanations

    more

    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
    ToBounds
    -0.52
    MinWidth
    -0.50
     harder
    -0.50
     longer
    -0.49
     становника
    -0.48
     kiệm
    -0.48
     shorter
    -0.47
    stě
    -0.47
     dużo
    -0.47
     greater
    -0.46
    POSITIVE LOGITS
    DockStyle
    0.62
    期刊论文
    0.60
     autorytatywna
    0.59
    Дереккөздер
    0.57
     legitimacy
    0.56
     scolaires
    0.56
    SizeF
    0.55
     fluidity
    0.55
    influence
    0.54
    complexContent
    0.54
    Activations Density 0.002%

    No Known Activations