© 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. 4-CLT-HP
    7. 572
    Prev
    Next
    INDEX
    Explanations

    usage/processes

    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
     nahilalakip
    -0.70
     архивлан
    -0.68
    脚注の使い方
    -0.65
    DockStyle
    -0.61
    AndEndTag
    -0.57
    GRANTED
    -0.54
    المناصب
    -0.52
     الحره
    -0.52
    stdc
    -0.52
     ujednoznacz
    -0.52
    POSITIVE LOGITS
     smartly
    0.59
     rightly
    0.57
     wisely
    0.57
     sensibly
    0.56
     logically
    0.56
     knowingly
    0.56
     flatly
    0.55
     correctly
    0.55
     indiv
    0.54
     rhetor
    0.54
    Activations Density 0.015%

    No Known Activations