© 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. 1863
    Prev
    Next
    INDEX
    Explanations

    system

    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
    MigrationBuilder
    -0.65
    Autoritní
    -0.60
    balleur
    -0.60
     shouldBe
    -0.59
    oweit
    -0.59
     disambiguazione
    -0.59
    Identyfik
    -0.59
    >\<^
    -0.59
    AndEndTag
    -0.58
    openConnection
    -0.57
    POSITIVE LOGITS
    KommentareTeilen
    0.45
    IBOutlet
    0.44
     Simultaneously
    0.43
    ubu
    0.43
     يتيمه
    0.39
    ழ
    0.39
    chengladbach
    0.39
    stackSize
    0.38
    gdx
    0.38
    setVerticalGroup
    0.37
    Activations Density 0.000%

    No Known Activations