© 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. 92939
    Prev
    Next
    INDEX
    Explanations

    onate

    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
    ///</
    -0.94
    onate
    -0.90
    pires
    -0.84
    letes
    -0.84
    SourceChecksum
    -0.84
    stood
    -0.82
    UserScript
    -0.81
    idate
    -0.77
    strate
    -0.77
    Alike
    -0.76
    POSITIVE LOGITS
    middels
    0.51
    jeka
    0.48
     termica
    0.46
     ulei
    0.44
    code
    0.43
     Hebron
    0.42
    y
    0.42
     jude
    0.42
    הם
    0.41
     noastră
    0.41
    Activations Density 0.095%

    No Known Activations