© 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. 0-CLT-HP
    7. 43152
    Prev
    Next
    INDEX
    Explanations

    collecting

    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
     collecting
    -1.03
    SourceChecksum
    -0.70
    queryInterface
    -0.54
    GraphicsUnit
    -0.54
     collect
    -0.53
    verwijspagina
    -0.52
    ly
    -0.51
     IBOutlet
    -0.51
     sets
    -0.48
    ₁,
    -0.47
    POSITIVE LOGITS
    RegressionTest
    0.63
     Session
    0.59
    Session
    0.58
     cerebellum
    0.57
    zeba
    0.57
    ิลป
    0.56
     Rodrig
    0.56
    Życiorys
    0.56
    $_['
    0.56
    HIRE
    0.55
    Activations Density 0.081%

    No Known Activations