© 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. 3635
    Prev
    Next
    INDEX
    Explanations

    code

    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
    StoreMessageInfo
    -0.57
    ukone
    -0.56
    refront
    -0.52
    Azur
    -0.51
    HasAnnotation
    -0.51
     propOrder
    -0.51
    Билгалдахарш
    -0.50
    otras
    -0.50
     bag
    -0.50
    ItemBackground
    -0.49
    POSITIVE LOGITS
     تضيفلها
    0.74
    featureID
    0.60
    enderror
    0.59
     defStyle
    0.59
    ParallelGroup
    0.55
     degrés
    0.53
    YC
    0.49
    (&:
    0.49
    IntoConstraints
    0.47
    gamma
    0.47
    Activations Density 0.001%

    No Known Activations