© 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. 0-CLT-HP
    7. 94830
    Prev
    Next
    INDEX
    Explanations

    informational texts

    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
     Efq
    -0.82
    IntoConstraints
    -0.73
     Houſe
    -0.71
     Anſ
    -0.70
     Polda
    -0.68
     Theſe
    -0.68
     autorytatywna
    -0.67
     cauſe
    -0.67
     houſe
    -0.66
    homonymie
    -0.65
    POSITIVE LOGITS
     propOrder
    0.52
    uxxxx
    0.50
    édie
    0.44
     ig
    0.43
    0.43
     pas
    0.42
     carried
    0.42
    pas
    0.42
    Hence
    0.42
    hoga
    0.42
    Activations Density 1.676%

    No Known Activations