© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1269
    Prev
    Next
    INDEX
    Explanations

    so

    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
     للمعارف
    -0.75
     فريبيس
    -0.74
    \{\\
    -0.68
     fratelli
    -0.67
     dévelo
    -0.65
     Вікі
    -0.65
    AnchorStyles
    -0.65
     Monfieur
    -0.65
    AutoScaleMode
    -0.64
     يتيمه
    -0.64
    POSITIVE LOGITS
     extremely
    0.60
     well
    0.59
     highly
    0.57
     incredibly
    0.57
     made
    0.57
     similar
    0.56
     significant
    0.56
     focused
    0.55
     able
    0.55
     brought
    0.54
    Activations Density 0.139%

    No Known Activations