© 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. 92086
    Prev
    Next
    INDEX
    Explanations

    idel

    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
    kuuta
    -0.55
    EUR
    -0.54
    Autoritní
    -0.53
    eb
    -0.52
    ih
    -0.51
    eh
    -0.50
    eon
    -0.50
     onlyOwner
    -0.50
    redited
    -0.50
    cherry
    -0.48
    POSITIVE LOGITS
    Portail
    0.58
     jsPsych
    0.56
     EconPapers
    0.54
     marcato
    0.46
     mosso
    0.45
     CAST
    0.45
     molten
    0.44
    elerik
    0.43
    nms
    0.43
     Aware
    0.43
    Activations Density 0.001%

    No Known Activations