© 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. 43609
    Prev
    Next
    INDEX
    Explanations

    sement

    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
    itarian
    -0.80
    aneous
    -0.79
    ophone
    -0.75
    sement
    -0.73
    acular
    -0.69
    itability
    -0.68
    sibilities
    -0.66
    ization
    -0.66
    WSER
    -0.65
    IntoConstraints
    -0.65
    POSITIVE LOGITS
    Personensuche
    0.70
     Unto
    0.58
    canestro
    0.58
     defaultstate
    0.56
     proie
    0.53
    Sub
    0.51
     Plays
    0.51
     döner
    0.51
     terminée
    0.50
     mourut
    0.50
    Activations Density 1.579%

    No Known Activations