© 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. 5-CLT-HP
    7. 96422
    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
     sondern
    -0.63
    verständlich
    -0.59
     gången
    -0.53
     behövs
    -0.51
     hoppas
    -0.51
    ginald
    -0.51
    HostException
    -0.50
    IsMutable
    -0.50
     hanem
    -0.49
     bakgrund
    -0.49
    POSITIVE LOGITS
     and
    0.97
    CPtr
    0.60
    and
    0.60
     itself
    0.56
     gyhoeddwyd
    0.54
     Exacts
    0.53
    AutoScale
    0.52
    مصادر
    0.50
     And
    0.50
    leth
    0.48
    Activations Density 0.003%

    No Known Activations