© 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. 42676
    Prev
    Next
    INDEX
    Explanations

    medical text

    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
     The
    -0.54
     I
    -0.51
    lling
    -0.51
     to
    -0.49
     De
    -0.47
     You
    -0.45
    ledge
    -0.45
     So
    -0.45
     
    -0.45
     Me
    -0.44
    POSITIVE LOGITS
     ་་
    0.97
     myſelf
    0.95
     itſelf
    0.90
     Efq
    0.88
     theſe
    0.85
     fubject
    0.84
     houſe
    0.84
     ―――――
    0.83
     neceff
    0.82
     unſ
    0.82
    Activations Density 0.127%

    No Known Activations