© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44014
    Prev
    Next
    INDEX
    Explanations

    scientific regulatory processes

    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
     scope
    -0.46
     of
    -0.37
     tắc
    -0.36
    key
    -0.35
    ↵
    -0.35
     off
    -0.35
    是
    -0.35
    疇
    -0.34
     brief
    -0.34
     сердца
    -0.33
    POSITIVE LOGITS
    SequentialGroup
    0.84
    Datuak
    0.83
    KommentareTeilen
    0.82
     виправивши
    0.81
    ########.
    0.81
     lenker
    0.80
    protoc
    0.77
     rospy
    0.77
    abestanden
    0.77
    CppMethod
    0.76
    Activations Density 0.618%

    No Known Activations