© 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. 20-CLT-HP
    7. 72193
    Prev
    Next
    INDEX
    Explanations

    Code and research documentation

    np_max-act-logits · 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
    enderror
    -0.63
     otomatig
    -0.61
     GenerationType
    -0.59
     kuni
    -0.53
    writeFieldEnd
    -0.53
    resave
    -0.51
    bestos
    -0.51
     Laval
    -0.51
    titleMargin
    -0.51
     venter
    -0.50
    POSITIVE LOGITS
     Anfitrión
    0.52
    AxisAlignment
    0.51
    红色
    0.49
    WEBPACK
    0.46
     initComponents
    0.46
     nah
    0.44
     editText
    0.43
    unchecked
    0.43
     Hornets
    0.43
    ccato
    0.42
    Activations Density 0.000%

    No Known Activations