© 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. 1-CLT-HP
    7. 9119
    Prev
    Next
    INDEX
    Explanations

    case

    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
     of
    -0.53
    esis
    -0.46
    lised
    -0.40
    isme
    -0.40
    IMENTO
    -0.38
    avanje
    -0.38
    itates
    -0.38
    setPref
    -0.36
    kých
    -0.36
     soins
    -0.36
    POSITIVE LOGITS
     AssemblyVersion
    0.90
     StringTokenizer
    0.88
     InputDecoration
    0.86
    AndEndTag
    0.81
    MessageTagHelper
    0.81
     GoogleFonts
    0.80
     للمعارف
    0.80
     saites
    0.78
     BoxFit
    0.77
     فريبيس
    0.76
    Activations Density 0.578%

    No Known Activations