© 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. 1-CLT-HP
    7. 10959
    Prev
    Next
    INDEX
    Explanations

    Harmful/negative concepts

    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
    ValueStyle
    -1.01
     GenerationType
    -0.96
    AccessFile
    -0.88
    NOPQRST
    -0.76
    GenerationType
    -0.71
    TestingModule
    -0.70
    SuccessListener
    -0.69
    省市镇
    -0.69
    AccessorTable
    -0.68
     NSCoder
    -0.68
    POSITIVE LOGITS
     use
    0.43
    hook
    0.43
    KEYCODE
    0.42
     dating
    0.42
     Wi
    0.41
     consum
    0.40
     loyal
    0.40
     hook
    0.40
     bra
    0.39
     yours
    0.39
    Activations Density 0.021%

    No Known Activations