© 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. 4609
    Prev
    Next
    INDEX
    Explanations

    team

    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
     amarillas
    -0.58
     compito
    -0.54
     morire
    -0.54
    Atsauces
    -0.53
    Scénario
    -0.53
    twimg
    -0.52
     jambe
    -0.52
    utilisons
    -0.51
     vaisselle
    -0.50
    Diweddarwch
    -0.48
    POSITIVE LOGITS
     leaders
    0.56
    thenia
    0.55
    зулта
    0.54
     leadership
    0.53
    TestBed
    0.51
    PrototypeOf
    0.51
    htë
    0.51
     teams
    0.50
     organization
    0.50
    BeginContext
    0.50
    Activations Density 0.003%

    No Known Activations