© 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. 1-CLT-HP
    7. 10621
    Prev
    Next
    INDEX
    Explanations

    age and security

    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
     bershka
    -0.66
     myſelf
    -0.63
     مرئيه
    -0.60
     initComponents
    -0.59
     raiſ
    -0.59
     ſte
    -0.55
     rodríguez
    -0.54
    textAppearance
    -0.54
     ―――――
    -0.53
     Age
    -0.53
    POSITIVE LOGITS
    ing
    0.62
    OGND
    0.50
     Fix
    0.50
     Deal
    0.50
     Working
    0.48
     Predict
    0.48
     Question
    0.47
    findpost
    0.47
     Offer
    0.47
     Deb
    0.47
    Activations Density 0.003%

    No Known Activations