© 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. 2033
    Prev
    Next
    INDEX
    Explanations

    programming 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
     setAddress
    -0.56
    stości
    -0.54
    VIAF
    -0.47
    darah
    -0.47
    čnosti
    -0.47
     humanas
    -0.45
    Odour
    -0.44
    Locality
    -0.43
     mema
    -0.43
     sguardo
    -0.43
    POSITIVE LOGITS
     архивлан
    0.69
    AndEndTag
    0.69
    .*")]
    0.63
     '\\;'
    0.60
    ьаж
    0.60
    elemField
    0.60
    StoryboardSegue
    0.59
    acyjne
    0.58
    pédie
    0.58
    ModelAdmin
    0.58
    Activations Density 0.001%

    No Known Activations