© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4881
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Personendaten
    -0.71
    WithIOException
    -0.63
    afterEach
    -0.56
    Destroyed
    -0.56
    Reuse
    -0.54
     død
    -0.53
     död
    -0.52
     Extinction
    -0.52
     tắc
    -0.51
     podjela
    -0.51
    POSITIVE LOGITS
     متعلقه
    0.73
    :+:
    0.61
    +#+#
    0.60
     ElementRef
    0.60
    ]")]
    0.57
    makeConstraints
    0.57
    ⎨
    0.54
     חיצוניים
    0.53
    once
    0.53
    orianCalendar
    0.52
    Activations Density 0.007%

    No Known Activations