© 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. 5-CLT-HP
    7. 3847
    Prev
    Next
    INDEX
    Explanations

    similarity/matching

    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
     referenties
    -0.60
    الدراسه
    -0.54
    Географиясе
    -0.50
     AssemblyCompany
    -0.50
     cartila
    -0.48
     gynhyrchwyd
    -0.48
    rophilic
    -0.48
    useNewUrlParser
    -0.47
     emulsions
    -0.46
    ustainable
    -0.45
    POSITIVE LOGITS
     שוליים
    0.66
    XmlAccessType
    0.59
    migrationBuilder
    0.59
     FIGURE
    0.56
    InputBorder
    0.55
    AndEndTag
    0.51
    BEST
    0.51
    FIGURE
    0.51
     BEST
    0.49
     intptr
    0.49
    Activations Density 0.016%

    No Known Activations