© 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. 5-CLT-HP
    7. 3021
    Prev
    Next
    INDEX
    Explanations

    of

    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
    IntoConstraints
    -0.96
    awtextra
    -0.71
    \{\\
    -0.68
     المعيارى
    -0.68
    FormTagHelper
    -0.67
    windowFixed
    -0.65
    AddTagHelper
    -0.65
    endpush
    -0.64
    WebVitals
    -0.64
     الحره
    -0.63
    POSITIVE LOGITS
     several
    0.59
     many
    0.58
     both
    0.56
     multiple
    0.52
     reported
    0.49
     other
    0.48
     licensees
    0.47
     users
    0.47
     known
    0.46
     resident
    0.45
    Activations Density 0.004%

    No Known Activations