© 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. 0-CLT-HP
    7. 97410
    Prev
    Next
    INDEX
    Explanations

    phase

    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
    phase
    -1.07
    CloseOperation
    -0.74
     légiti
    -0.73
     quelcon
    -0.71
    帖最后由
    -0.71
    abatic
    -0.68
    quared
    -0.65
    väg
    -0.65
    grunns
    -0.65
    PHASE
    -0.64
    POSITIVE LOGITS
    parsedMessage
    0.60
     Diony
    0.56
    PC
    0.55
    setDo
    0.54
     Masonic
    0.54
    SpringBoot
    0.53
    disposing
    0.53
     frappe
    0.53
     STC
    0.52
    Expose
    0.52
    Activations Density 0.377%

    No Known Activations