© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76290
    Prev
    Next
    INDEX
    Explanations

    poss/sess

    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
    modities
    -0.63
     capes
    -0.62
     knots
    -0.62
    Portail
    -0.61
    OGND
    -0.60
    alist
    -0.60
     Tramp
    -0.60
     sequins
    -0.57
    mapStateToProps
    -0.57
     triglycerides
    -0.56
    POSITIVE LOGITS
    webElementXpaths
    0.66
     utafitiHapana
    0.63
     GenerationType
    0.60
    pushFollow
    0.59
    InjectAttribute
    0.59
     ComVisible
    0.54
    titleMargin
    0.54
    Referencies
    0.52
     numerus
    0.52
     CreateTagHelper
    0.50
    Activations Density 0.003%

    No Known Activations