© 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. 5
    Prev
    Next
    INDEX
    Explanations

    barometer

    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
    somewhat
    -1.20
    slightly
    -1.15
     Somewhat
    -1.13
     somewhat
    -1.13
     slightly
    -1.12
    Somewhat
    -1.09
    Slightly
    -1.09
     trochę
    -1.09
     Slightly
    -1.05
     nieco
    -1.02
    POSITIVE LOGITS
     millions
    0.50
     countless
    0.50
     virtually
    0.48
    事を
    0.46
    lo
    0.44
    !
    0.44
     vast
    0.43
    pso
    0.43
     thousands
    0.43
    かわらず
    0.42
    Activations Density 0.051%

    No Known Activations