© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9047
    Prev
    Next
    INDEX
    Explanations

    finds

    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
     finds
    -1.64
    finds
    -1.39
     Finds
    -1.32
     find
    -1.15
    find
    -1.02
     FIND
    -0.99
     finding
    -0.96
    Find
    -0.93
    FIND
    -0.90
     Find
    -0.90
    POSITIVE LOGITS
     nôtre
    0.65
    SpringBootTest
    0.57
    ReusableCell
    0.54
    Fordítás
    0.53
    //
    0.53
     ſte
    0.53
    unggu
    0.52
    setViewName
    0.52
    ۜ
    0.51
    estacks
    0.51
    Activations Density 0.003%

    No Known Activations