© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93440
    Prev
    Next
    INDEX
    Explanations

    random text snippets

    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
     compared
    -0.47
     therefore
    -0.47
     iprot
    -0.46
    skapet
    -0.46
     chronique
    -0.44
     cubanos
    -0.44
     double
    -0.44
     even
    -0.44
    ровая
    -0.43
    hena
    -0.43
    POSITIVE LOGITS
    GOTREF
    0.70
     насељу
    0.69
     Biôgrafia
    0.68
    ThroughAttribute
    0.67
    UnusedPrivate
    0.64
    yntaxException
    0.62
    ergies
    0.61
    StoryboardSegue
    0.60
    UrlEncoded
    0.60
     Meksiku
    0.60
    Activations Density 0.005%

    No Known Activations