© 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. 4-CLT-HP
    7. 2497
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
     متعلقه
    -0.79
     AssemblyCompany
    -0.62
    ParallelGroup
    -0.59
     be
    -0.58
     devenus
    -0.55
     fraî
    -0.55
     appunto
    -0.54
    lijkse
    -0.53
     ouvertes
    -0.52
     épais
    -0.51
    POSITIVE LOGITS
     or
    0.79
    featureID
    0.70
     nahilalakip
    0.68
     Roskov
    0.63
    ThroughAttribute
    0.62
    Abitanti
    0.61
     Assignee
    0.59
     estimés
    0.58
     Италијани
    0.57
    kwds
    0.57
    Activations Density 0.002%

    No Known Activations