© 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. 4842
    Prev
    Next
    INDEX
    Explanations

    feel

    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
     ModelExpression
    -0.86
     незавершена
    -0.67
    RectangleBorder
    -0.66
     InputDecoration
    -0.66
     AttributeSet
    -0.63
     ElementRef
    -0.57
    InstanceState
    -0.56
    Personendaten
    -0.56
     genomen
    -0.56
     pessimism
    -0.56
    POSITIVE LOGITS
    unmodifiable
    0.55
     thicker
    0.52
     heavier
    0.51
    featureID
    0.48
    AnchorStyles
    0.47
    violi
    0.47
     weighty
    0.47
     cushi
    0.46
     AssemblyProduct
    0.45
     '\\;'
    0.45
    Activations Density 0.002%

    No Known Activations