© 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. 94592
    Prev
    Next
    INDEX
    Explanations

    Chan

    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
    出版年
    -0.82
     Welles
    -0.71
     saites
    -0.67
    ipedi
    -0.60
    orghini
    -0.58
    sizeCache
    -0.58
    ptonshire
    -0.58
    +:+
    -0.58
    posites
    -0.57
    المشاركات
    -0.57
    POSITIVE LOGITS
    CompleteListener
    0.59
    :✨
    0.57
    SuccessListener
    0.57
     Auf
    0.46
    Normdaten
    0.44
    Geografia
    0.43
    Eksterne
    0.43
    audiovisuel
    0.42
     gestes
    0.42
    ligkeit
    0.41
    Activations Density 0.000%

    No Known Activations