© 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. 0-CLT-HP
    7. 42083
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    est
    -0.47
    </em>
    -0.45
    sel
    -0.44
    առ
    -0.44
    NSUserDefaults
    -0.43
    i
    -0.43
    au
    -0.42
    </strong>
    -0.42
    es
    -0.42
    ca
    -0.41
    POSITIVE LOGITS
    parsedMessage
    0.84
    ainville
    0.83
     Wikimedijinoj
    0.81
    oredCriteria
    0.76
    obiety
    0.73
    lgari
    0.71
    Jereo
    0.71
    kész
    0.71
     AssemblyCompany
    0.69
     CreateTagHelper
    0.69
    Activations Density 1.810%

    No Known Activations