© 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. 4712
    Prev
    Next
    INDEX
    Explanations

    set

    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
     الحره
    -0.84
     propOrder
    -0.77
     BoxDecoration
    -0.75
    aarrggbb
    -0.74
    enumi
    -0.74
    TagMode
    -0.67
    sedown
    -0.66
     precedents
    -0.66
     forceps
    -0.65
    цездатний
    -0.63
    POSITIVE LOGITS
     bar
    0.45
     base
    0.45
     kitchen
    0.42
     viewDidLoad
    0.42
     casino
    0.42
    base
    0.42
     deck
    0.41
     Radio
    0.41
     pub
    0.40
    sidemargin
    0.40
    Activations Density 0.003%

    No Known Activations