© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4198
    Prev
    Next
    INDEX
    Explanations

    in

    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
     فريبيس
    -0.79
     <=",
    -0.70
    complexContent
    -0.69
    ftagPool
    -0.67
     GenerationType
    -0.65
     الحره
    -0.61
    yntaxException
    -0.60
    ExtendWith
    -0.58
    ClientRect
    -0.58
     للمعارف
    -0.57
    POSITIVE LOGITS
    providedIn
    0.49
     invokingState
    0.47
    initComponents
    0.45
     CanadaChoose
    0.43
    範圍
    0.41
    Rüyada
    0.40
     orgánica
    0.40
    CppMethod
    0.40
     verrez
    0.40
    abestanden
    0.40
    Activations Density 0.005%

    No Known Activations