© 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. 75972
    Prev
    Next
    INDEX
    Explanations

    beginnings of titles/sections

    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
     مرئيه
    -0.83
    GEBURTSDATUM
    -0.71
    TestingModule
    -0.71
     صوتيه
    -0.71
    EnableWeb
    -0.67
     ExecuteAsync
    -0.62
    IntoConstraints
    -0.60
    istoitu
    -0.59
    RepeatedField
    -0.59
    XmlAccessType
    -0.58
    POSITIVE LOGITS
     He
    0.60
    Us
    0.52
     Us
    0.52
     lontano
    0.50
     think
    0.50
    think
    0.48
     Wizard
    0.48
    us
    0.48
    He
    0.47
     us
    0.46
    Activations Density 0.001%

    No Known Activations