© 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. 5-CLT-HP
    7. 96810
    Prev
    Next
    INDEX
    Explanations

    "best part"

    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
    Personendaten
    -0.86
    ///</
    -0.70
     "..\..\..\
    -0.70
    PMailer
    -0.69
    GTCX
    -0.68
     Мексичка
    -0.65
    UnknownFieldSet
    -0.64
    Ārējās
    -0.63
    protoimpl
    -0.63
    UnusedPrivate
    -0.63
    POSITIVE LOGITS
     for
    0.51
     too
    0.46
     ricordi
    0.44
    bble
    0.40
    aguas
    0.40
    ագրություններ
    0.39
     mû
    0.39
     Uniti
    0.39
     estúdio
    0.39
    แต
    0.38
    Activations Density 0.001%

    No Known Activations