© 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. 98234
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     torta
    -0.52
    stonia
    -0.42
    Życiorys
    -0.40
    strijden
    -0.40
     region
    -0.40
    InvalidProtocol
    -0.38
    gerea
    -0.38
    southern
    -0.37
    fleisch
    -0.36
    ணை
    -0.36
    POSITIVE LOGITS
    AnchorStyles
    0.90
    tagHelperRunner
    0.88
    DockStyle
    0.85
    SourceChecksum
    0.82
    
    0.80
    AddTagHelper
    0.79
    KommentareTeilen
    0.79
    matchCondition
    0.77
    mybatisplus
    0.74
    ArrowToggle
    0.74
    Activations Density 0.029%

    No Known Activations