© 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. 5-CLT-HP
    7. 5242
    Prev
    Next
    INDEX
    Explanations

    legal matters

    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
     ligiloj
    -0.51
    <?
    -0.49
    träd
    -0.47
    ✭✭
    -0.45
    copus
    -0.45
    ollectionView
    -0.45
     merito
    -0.44
    URIDAD
    -0.44
     salut
    -0.44
    κρι
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.75
    XmlAccessType
    0.63
    новниш
    0.62
     réessayer
    0.60
    CppCodeGen
    0.59
    DropTable
    0.57
    EVEN
    0.56
    tvguidetime
    0.56
     <<<<<<<<<<<<<<
    0.55
    //</
    0.54
    Activations Density 0.026%

    No Known Activations