© 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. 0-CLT-HP
    4. 41048
    Prev
    Next
    INDEX
    Explanations

    dangerous

    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
     dangerous
    -1.65
    dangerous
    -1.62
     Dangerous
    -1.45
     dangereux
    -1.41
    Dangerous
    -1.38
     peligroso
    -1.33
     danger
    -1.32
     Danger
    -1.20
    Danger
    -1.18
     peligros
    -1.16
    POSITIVE LOGITS
    Демографія
    0.68
    ness
    0.63
    DataPropertyName
    0.52
    NESS
    0.51
    AfterClass
    0.49
    UrlResolution
    0.48
    LookAnd
    0.48
     Da
    0.47
    ❉
    0.47
     bio
    0.47
    Activations Density 0.192%

    No Known Activations