© 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. 20-CLT-HP
    7. 71702
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · 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
     houſe
    -0.68
     ſche
    -0.63
     ſeveral
    -0.63
     genio
    -0.61
     ſmall
    -0.59
     biographical
    -0.58
     poffible
    -0.58
     fubject
    -0.57
     occaf
    -0.57
     serialization
    -0.57
    POSITIVE LOGITS
     Emp
    0.58
     käytet
    0.54
     Ex
    0.54
     Sele
    0.53
     Con
    0.53
     Imp
    0.52
     Rec
    0.50
     Sim
    0.50
     lisäksi
    0.50
     En
    0.49
    Activations Density 0.002%

    No Known Activations