© 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. 4677
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    |()
    -0.65
    ISupport
    -0.64
     कैसी
    -0.58
    mota
    -0.57
     Мексичка
    -0.55
    erover
    -0.53
    IFO
    -0.53
    thard
    -0.52
     bağlantılar
    -0.52
    ταν
    -0.52
    POSITIVE LOGITS
    iNdEx
    0.55
    penup
    0.53
    siąż
    0.47
     charged
    0.46
    ,
    0.46
    udayaan
    0.45
    sizeCache
    0.44
    Билгалдахарш
    0.44
    ngOnInit
    0.44
    keyboardType
    0.43
    Activations Density 0.001%

    No Known Activations