© 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. 4-CLT-HP
    7. 557
    Prev
    Next
    INDEX
    Explanations

    Code/identifiers

    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
     linkovi
    -0.58
    NullCheck
    -0.54
    siga
    -0.54
     Szen
    -0.54
    MarshalTo
    -0.54
     SYMP
    -0.53
    Solved
    -0.52
     AssemblyTitle
    -0.52
    Datuak
    -0.52
     TestBed
    -0.51
    POSITIVE LOGITS
     otomatig
    0.59
    AsUp
    0.56
    AndEndTag
    0.56
    setVerticalGroup
    0.47
    PMailer
    0.46
     '\\;'
    0.46
    InSection
    0.46
     connexes
    0.46
     Paris
    0.45
    脚注の使い方
    0.45
    Activations Density 0.003%

    No Known Activations