© 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. 1-CLT-HP
    7. 9028
    Prev
    Next
    INDEX
    Explanations

    pear

    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
     Pear
    -1.41
     pear
    -1.31
    pear
    -1.26
    Pear
    -1.23
     PEAR
    -0.85
     pearl
    -0.59
     Pearl
    -0.59
     Pearce
    -0.54
    Pearl
    -0.54
     perles
    -0.52
    POSITIVE LOGITS
     betweenstory
    1.14
    InitVars
    0.98
     незавершена
    0.96
    AndroidJUnit
    0.94
     تضيفلها
    0.89
    RenderAtEndOf
    0.88
    Chham
    0.88
     itſelf
    0.86
    Enllaces
    0.85
     Chwiliwch
    0.85
    Activations Density 0.203%

    No Known Activations