© 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. 5-CLT-HP
    7. 4523
    Prev
    Next
    INDEX
    Explanations

    warehouses

    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
    niająca
    -0.66
    SBATCH
    -0.64
    ContextHolder
    -0.63
    SceneManagement
    -0.62
    اریخ
    -0.60
     AssemblyTitle
    -0.57
    ayaquil
    -0.57
     Hooper
    -0.57
    dbo
    -0.57
     Paglinawan
    -0.56
    POSITIVE LOGITS
    BeginInit
    0.53
    ~=
    0.45
     zout
    0.45
     buckling
    0.43
    REFERENCE
    0.43
     bush
    0.42
    agencies
    0.42
    __*/
    0.41
    agency
    0.41
    borderFill
    0.41
    Activations Density 0.002%

    No Known Activations