© 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. 4-CLT-HP
    7. 1645
    Prev
    Next
    INDEX
    Explanations

    Negative/strong words

    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
    ,
    -0.41
    PRIOR
    -0.41
    Sie
    -0.41
     Sie
    -0.40
     anledning
    -0.40
    assertNotNull
    -0.40
    CodeAttribute
    -0.40
    colata
    -0.40
     esto
    -0.39
    жалуйста
    -0.39
    POSITIVE LOGITS
    ingly
    1.47
    ings
    1.34
    ers
    1.33
    ership
    1.08
    ering
    1.04
    ered
    1.00
    ERS
    0.96
    INGS
    0.91
    ing
    0.91
    ery
    0.90
    Activations Density 0.012%

    No Known Activations