© 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. 20-CLT-HP
    7. 76193
    Prev
    Next
    INDEX
    Explanations

    Formal/informational texts

    np_max-act-logits · 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
     chi̍t
    -0.61
     Chwiliwch
    -0.60
    AndroidJUnit
    -0.53
    writeField
    -0.52
    Oneof
    -0.52
    Personendaten
    -0.52
    msgTypes
    -0.52
    clerview
    -0.51
    endy
    -0.49
     bezeichneter
    -0.48
    POSITIVE LOGITS
     allowed
    0.57
     elevating
    0.57
     allowing
    0.56
    allowed
    0.55
     permitting
    0.55
    [++
    0.53
     Playboy
    0.51
    aryana
    0.50
    allowing
    0.49
    hooks
    0.49
    Activations Density 0.001%

    No Known Activations