© 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. 1-CLT-HP
    7. 10070
    Prev
    Next
    INDEX
    Explanations

    was

    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
     initially
    -0.60
     dévelo
    -0.58
     survie
    -0.57
    GORITH
    -0.56
     mélanger
    -0.55
    بوابة
    -0.55
     supuestamente
    -0.55
    osexual
    -0.54
     étanche
    -0.54
     definitely
    -0.53
    POSITIVE LOGITS
    AutoScaleMode
    0.55
    veral
    0.54
    DeleteBehavior
    0.51
     resourceCulture
    0.50
    antMatchers
    0.48
    got
    0.47
    Koordinaten
    0.46
    setVerticalGroup
    0.46
     ThemeData
    0.46
     AssemblyCompany
    0.45
    Activations Density 0.006%

    No Known Activations