© 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. 95076
    Prev
    Next
    INDEX
    Explanations

    differences and changes

    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
     finger
    -0.77
     varying
    -0.69
     Finger
    -0.68
     تانيه
    -0.68
     larger
    -0.66
     betweenstory
    -0.65
     sum
    -0.63
    Finger
    -0.62
     varied
    -0.59
    dır
    -0.59
    POSITIVE LOGITS
    ,
    0.50
    time
    0.50
    bed
    0.48
    fromCharCode
    0.48
     ==
    0.47
    vascular
    0.47
    ộn
    0.46
     <
    0.46
    ligkeit
    0.45
    .
    0.45
    Activations Density 0.117%

    No Known Activations