© 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. 4-CLT-HP
    7. 2080
    Prev
    Next
    INDEX
    Explanations

    ( edit

    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
    addCriterion
    -0.72
     gynhyrchwyd
    -0.65
    ?")
    -0.63
    Hentet
    -0.62
     invokingState
    -0.62
    يكب
    -0.62
     ujednoznacz
    -0.61
    principalColumn
    -0.60
    =")
    -0.60
    EndGlobalSection
    -0.59
    POSITIVE LOGITS
    liath
    0.48
     MCM
    0.45
     Bulls
    0.45
     تضيفلها
    0.43
     مشين
    0.43
    ництво
    0.40
    oldown
    0.40
    xH
    0.39
    koin
    0.39
     Stare
    0.38
    Activations Density 0.001%

    No Known Activations