© 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. 97255
    Prev
    Next
    INDEX
    Explanations

    remove

    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
     remove
    -1.10
    remove
    -0.85
     Remove
    -0.77
     get
    -0.72
     REMOVE
    -0.69
     prochaines
    -0.69
    removal
    -0.67
     procédures
    -0.67
     supplémentaires
    -0.66
     creazione
    -0.66
    POSITIVE LOGITS
     the
    0.63
     tons
    0.63
     treated
    0.53
    makeConstraints
    0.50
     treats
    0.48
    endphp
    0.48
     lots
    0.47
    issors
    0.47
    HtmlAttribute
    0.46
     some
    0.46
    Activations Density 0.019%

    No Known Activations