© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97273
    Prev
    Next
    INDEX
    Explanations

    Reducing

    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
    Reducing
    -0.82
    reducing
    -0.79
    reduction
    -0.76
    Reduction
    -0.72
     Reducing
    -0.58
     REDUC
    -0.58
     REDUCTION
    -0.58
    ParallelGroup
    -0.55
    Reduced
    -0.55
     defaultstate
    -0.54
    POSITIVE LOGITS
     espirituales
    0.64
    s
    0.63
    getDescription
    0.59
     militaires
    0.59
     médicas
    0.57
     Dosen
    0.53
    irot
    0.53
    前言
    0.52
     églises
    0.52
    sen
    0.52
    Activations Density 0.107%

    No Known Activations