© 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. 4-CLT-HP
    7. 2680
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
    <bos>
    -0.80
     affected
    -0.49
     face
    -0.47
     cooling
    -0.46
     rein
    -0.46
     saites
    -0.45
     crown
    -0.43
    st
    -0.42
     skin
    -0.42
     screen
    -0.42
    POSITIVE LOGITS
     Roskov
    0.87
     supérieurs
    0.81
     réguli
    0.80
     démocr
    0.79
     automatiques
    0.70
     lèvres
    0.69
     fermés
    0.69
     élevées
    0.69
     rempliss
    0.68
     vectorielles
    0.68
    Activations Density 0.081%

    No Known Activations