© 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. 5-CLT-HP
    7. 94092
    Prev
    Next
    INDEX
    Explanations

    laughter

    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
    errHandler
    -0.54
    ,:),
    -0.52
     personnaliser
    -0.50
    urie
    -0.47
     invokingState
    -0.47
    >",
    -0.42
     Deutschlands
    -0.42
    corsi
    -0.41
    ure
    -0.41
    ",&
    -0.40
    POSITIVE LOGITS
    cats
    0.64
    OL
    0.63
    Cats
    0.63
    qrstuvwxyz
    0.62
     Cats
    0.59
     tanong
    0.56
    CAPS
    0.54
    brido
    0.52
     aimez
    0.51
    ollectionView
    0.51
    Activations Density 0.003%

    No Known Activations