© 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. 4606
    Prev
    Next
    INDEX
    Explanations

    use, usage, application

    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
     itſelf
    -0.73
    ]--;
    -0.61
     للاسماء
    -0.59
     fevere
    -0.59
     Jefus
    -0.57
     your
    -0.57
    })));
    -0.55
     ſmall
    -0.55
     widths
    -0.54
     purpoſe
    -0.54
    POSITIVE LOGITS
     to
    0.66
     no
    0.64
     defaultstate
    0.51
     Right
    0.51
     immediately
    0.49
     right
    0.49
    no
    0.48
     at
    0.48
    p
    0.47
     Immediately
    0.46
    Activations Density 0.002%

    No Known Activations