© 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. 0-CLT-HP
    7. 41377
    Prev
    Next
    INDEX
    Explanations

    multiplication

    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
    machung
    -0.66
     '\\;'
    -0.63
    sizeCache
    -0.62
    rasz
    -0.57
     Rowley
    -0.54
    zbęd
    -0.54
    CPE
    -0.52
    TintMode
    -0.51
    Estadio
    -0.51
    FCS
    -0.51
    POSITIVE LOGITS
    SequentialGroup
    0.92
    TestMethod
    0.59
    AndEndTag
    0.59
     صوتيه
    0.56
     الميل
    0.53
    MemoryWarning
    0.52
    modelBuilder
    0.52
     shouldBe
    0.52
     Galile
    0.49
     Defin
    0.49
    Activations Density 0.188%

    No Known Activations