© 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. 15824
    Prev
    Next
    INDEX
    Explanations

    aya

    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
    ChildScrollView
    -0.64
    pecker
    -0.58
    fortawesome
    -0.57
    ONESIA
    -0.56
    batore
    -0.56
    zeiro
    -0.54
    petto
    -0.54
    fiore
    -0.54
    houette
    -0.53
    findpost
    -0.52
    POSITIVE LOGITS
    Personensuche
    0.75
     assent
    0.54
     unlaw
    0.52
    Enf
    0.50
     imputed
    0.49
    MethodImpl
    0.48
     eccell
    0.48
     conservatism
    0.47
     rappers
    0.47
     endwhile
    0.46
    Activations Density 0.052%

    No Known Activations