© 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. 2573
    Prev
    Next
    INDEX
    Explanations

    as

    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
    usermodel
    -0.58
     ModelExpression
    -0.53
    ]")]
    -0.52
     Celui
    -0.52
     WaitForSeconds
    -0.50
    warzys
    -0.50
     Chwiliwch
    -0.50
    InstrumentedTest
    -0.50
     GenerationType
    -0.50
     defStyleAttr
    -0.49
    POSITIVE LOGITS
    sie
    0.66
    cy
    0.60
    th
    0.59
    ke
    0.58
    m
    0.57
    hr
    0.57
    ocyan
    0.56
    ph
    0.55
    gle
    0.55
    pin
    0.54
    Activations Density 0.004%

    No Known Activations