© 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. 5-CLT-HP
    7. 5454
    Prev
    Next
    INDEX
    Explanations

    common English words

    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
    >{@
    -0.80
    ">—
    -0.77
     חיצוניים
    -0.76
    /*
    -0.75
    Diweddarwch
    -0.73
    /**
    -0.68
    LookAnd
    -0.67
    AddTagHelper
    -0.65
     AllAfrica
    -0.65
     aDecoder
    -0.63
    POSITIVE LOGITS
     einzigartigen
    0.42
    ständen
    0.41
    Smarty
    0.41
    ={{
    0.40
     sonno
    0.39
    Aiheesta
    0.39
     traffico
    0.39
     desiderio
    0.38
     handleSubmit
    0.38
    Unique
    0.37
    Activations Density 0.000%

    No Known Activations