© 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. 13918
    Prev
    Next
    INDEX
    Explanations

    sort

    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
     sort
    -1.77
     Sort
    -1.56
     kind
    -1.53
    kind
    -1.52
    sort
    -1.51
    Sort
    -1.38
    Kind
    -1.34
     sorts
    -1.31
     Kind
    -1.24
     SORT
    -1.24
    POSITIVE LOGITS
    protoimpl
    0.78
     ExecuteAsync
    0.64
    الإنجليزية
    0.62
     }}}
    0.60
    ()]);
    0.59
     invokingState
    0.59
    AntiForgeryToken
    0.57
    AndEndTag
    0.56
     nahilalakip
    0.55
    parsedMessage
    0.55
    Activations Density 0.375%

    No Known Activations