© 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. 1-CLT-HP
    7. 11557
    Prev
    Next
    INDEX
    Explanations

    teaser

    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
    COUVER
    -0.91
    cipital
    -0.77
     Marburg
    -0.75
     متعلقه
    -0.74
    GEBURTSDATUM
    -0.64
    ciatore
    -0.63
    TintMode
    -0.60
    chila
    -0.60
     Baillargeon
    -0.59
     Fok
    -0.59
    POSITIVE LOGITS
    userdetails
    0.53
    jdons
    0.40
     Volkes
    0.40
    ModelForm
    0.40
    rungsseite
    0.40
     quarter
    0.40
    ナンバー
    0.40
     word
    0.39
    为人
    0.39
     dépenses
    0.39
    Activations Density 0.841%

    No Known Activations