© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91546
    Prev
    Next
    INDEX
    Explanations

    government/code

    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
     italienne
    -0.50
    hadas
    -0.47
    czaj
    -0.47
     anything
    -0.46
    anything
    -0.45
     entirely
    -0.44
     canadienne
    -0.43
     mergeFrom
    -0.42
    ритори
    -0.42
     Anything
    -0.41
    POSITIVE LOGITS
    TagMode
    1.02
    DataAnnotations
    0.84
     صوتيه
    0.75
    SourceChecksum
    0.75
     bezeichneter
    0.69
     AssemblyCompany
    0.66
     disambiguazione
    0.66
    bewerken
    0.65
     gaining
    0.63
    tagHelperRunner
    0.63
    Activations Density 0.002%

    No Known Activations