© 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. 5-CLT-HP
    7. 97222
    Prev
    Next
    INDEX
    Explanations

    per

    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
     bosons
    -0.47
    UVWXYZ
    -0.46
    יוון
    -0.46
     bombers
    -0.46
     bombings
    -0.43
    DataBind
    -0.42
     robberies
    -0.41
    #__
    -0.41
     murders
    -0.40
    かわらず
    -0.40
    POSITIVE LOGITS
    verwijspagina
    0.78
    Демографія
    0.68
     myſelf
    0.66
     Theſe
    0.62
     itſelf
    0.60
     Anſ
    0.60
    vernight
    0.58
    ients
    0.58
    ſelf
    0.57
    matchCondition
    0.57
    Activations Density 0.001%

    No Known Activations