© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 91641
    Prev
    Next
    INDEX
    Explanations

    Formal Writing

    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
    ")){
    
    -0.65
    HomeAsUpEnabled
    -0.61
    exitRule
    -0.59
    SourceChecksum
    -0.59
    proud
    -0.59
    WireFormatLite
    -0.58
    bootstrapcdn
    -0.57
    UnsafeEnabled
    -0.56
    "))
    
    -0.56
    findpost
    -0.56
    POSITIVE LOGITS
     action
    0.54
     attention
    0.51
    mulos
    0.49
    ecuted
    0.48
     gouver
    0.47
     IOError
    0.47
     concorso
    0.47
     consideration
    0.46
     diplomacy
    0.46
     use
    0.46
    Activations Density 0.000%

    No Known Activations