© 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. 92037
    Prev
    Next
    INDEX
    Explanations

    Lockheed

    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
    DOCTYPE
    -0.63
    setVerticalGroup
    -0.58
    localctx
    -0.54
     &___
    -0.51
    (_,
    -0.50
    قایناقلار
    -0.48
     propOrder
    -0.48
    yles
    -0.48
     Dox
    -0.47
     ruth
    -0.45
    POSITIVE LOGITS
    värr
    0.56
     Collins
    0.54
     كمان
    0.53
    enderror
    0.52
    richTextPanel
    0.50
     Martin
    0.49
    InstanceState
    0.49
     MARTIN
    0.47
    ";}
    0.47
    manned
    0.46
    Activations Density 0.002%

    No Known Activations