© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90829
    Prev
    Next
    INDEX
    Explanations

    language

    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
     bar
    -0.45
     bus
    -0.42
     pack
    -0.42
     email
    -0.42
     gab
    -0.40
    🏻
    -0.40
    cast
    -0.39
     existential
    -0.39
     ent
    -0.39
     spin
    -0.39
    POSITIVE LOGITS
    ècie
    0.82
    Diweddarwch
    0.81
     ostavi
    0.77
    sidemargin
    0.77
    GEBURTSDATUM
    0.74
    Kariera
    0.71
     autorytatywna
    0.71
     oreilles
    0.70
     purpoſe
    0.70
    IntoConstraints
    0.69
    Activations Density 0.044%

    No Known Activations