© 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. 0-CLT-HP
    7. 95008
    Prev
    Next
    INDEX
    Explanations

    ego

    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
     scales
    -0.72
    scales
    -0.51
    rust
    -0.46
     c
    -0.45
    egg
    -0.44
    ego
    -0.43
    ahal
    -0.41
    ..
    -0.40
    interest
    -0.39
    red
    -0.38
    POSITIVE LOGITS
     Monfieur
    1.09
     purpoſe
    1.03
     iſt
    0.97
     defaultstate
    0.97
     Efq
    0.96
     ſy
    0.96
     Eſ
    0.94
    ſelf
    0.93
     Jefus
    0.92
     pleaſure
    0.92
    Activations Density 0.942%

    No Known Activations