© 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. 91269
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    tvguidetime
    -0.61
     betweenstory
    -0.57
     kasarigan
    -0.55
    المناصب
    -0.52
    fxml
    -0.51
    CodedInputStream
    -0.50
     لاس
    -0.48
     cherchés
    -0.48
    Kaynakça
    -0.48
    #+#
    -0.46
    POSITIVE LOGITS
    емости
    0.51
     AssemblyCompany
    0.49
     Fleisch
    0.48
    chauff
    0.48
    nang
    0.47
    Permalink
    0.47
     Normdatei
    0.47
    displayquote
    0.47
    chequer
    0.45
    thenia
    0.45
    Activations Density 0.001%

    No Known Activations