© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 324
    Prev
    Next
    INDEX
    Explanations

    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
     referenties
    -0.82
     مشين
    -0.70
     يتيمه
    -0.69
    ⓧ
    -0.68
     bezeichneter
    -0.68
    enumii
    -0.67
     "..\..\..\
    -0.67
    }))
    -0.67
    BibitemShut
    -0.66
    ')):
    -0.65
    POSITIVE LOGITS
     vectorielle
    0.46
    transfer
    0.45
     superiore
    0.44
    لغة
    0.44
    tappe
    0.43
     transfer
    0.42
     urbaine
    0.42
    har
    0.42
    transaksi
    0.42
    かと
    0.41
    Activations Density 0.001%

    No Known Activations