© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 764
    Prev
    Next
    INDEX
    Explanations

    Mete

    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
    ʻ
    -0.51
     Mete
    -0.50
     Rizzo
    -0.50
     Moulton
    -0.49
    man
    -0.48
    fjspx
    -0.48
    unshift
    -0.47
    ester
    -0.47
     bronce
    -0.46
    ynı
    -0.46
    POSITIVE LOGITS
    multicolumn
    0.63
    InjectAttribute
    0.59
    WebVitals
    0.59
    offsetof
    0.55
    SFD
    0.54
    pexpr
    0.54
    losures
    0.53
     GetComponent
    0.51
     DBNull
    0.50
     Ause
    0.50
    Activations Density 0.029%

    No Known Activations