© 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. 46274
    Prev
    Next
    INDEX
    Explanations

    phase/stage

    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
     stage
    -1.37
     phase
    -1.26
     stages
    -1.23
     Stage
    -1.21
    stage
    -1.18
    phase
    -1.15
     phases
    -1.12
     Phase
    -1.11
    Stage
    -1.08
     STAGE
    -1.08
    POSITIVE LOGITS
     acrylique
    0.69
     féminine
    0.66
     chimie
    0.60
     لينك
    0.60
     rivi
    0.59
     périph
    0.58
    WebVitals
    0.56
     Trasp
    0.56
     wireType
    0.56
     campagna
    0.55
    Activations Density 0.022%

    No Known Activations