© 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. 0-CLT-HP
    7. 92423
    Prev
    Next
    INDEX
    Explanations

    completing tasks

    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
    ssystem
    -0.55
    atriz
    -0.55
    alised
    -0.54
    isable
    -0.54
    ņem
    -0.53
    Revenir
    -0.52
     approach
    -0.52
    yll
    -0.51
    SerializeField
    -0.51
    ismes
    -0.51
    POSITIVE LOGITS
    IsMutable
    0.60
     ProtoMessage
    0.59
     unknownFields
    0.57
    complexContent
    0.55
    IndentedString
    0.54
    Населення
    0.54
    catch
    0.53
     a
    0.51
    Personensuche
    0.51
    ollectionView
    0.50
    Activations Density 0.054%

    No Known Activations