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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4015
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
     للمعارف
    -0.85
    Personensuche
    -0.82
     дописавши
    -0.82
     otomatig
    -0.79
     незавершена
    -0.75
    RegistryLite
    -0.74
    NewUrlParser
    -0.73
     estekak
    -0.72
     himo
    -0.71
     ModelExpression
    -0.71
    POSITIVE LOGITS
     kids
    0.46
     AppCompatTheme
    0.45
     the
    0.44
    osse
    0.42
    ForRow
    0.42
     kid
    0.41
     sequence
    0.40
    ết
    0.40
    signol
    0.39
     h
    0.38
    Activations Density 0.001%

    No Known Activations