© 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. 4-CLT-HP
    7. 2178
    Prev
    Next
    INDEX
    Explanations

    anecdotal summaries using "one"

    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
     ſind
    -0.53
     purpoſe
    -0.53
    ALIA
    -0.53
    DotNet
    -0.52
    PreferredItem
    -0.51
    avadoc
    -0.50
    ILIA
    -0.50
    lect
    -0.48
    翻攝
    -0.48
    `]
    -0.47
    POSITIVE LOGITS
     that
    0.75
    !
    0.67
     CreateTagHelper
    0.63
    .
    0.62
    findpost
    0.58
    argout
    0.56
    ContentAsync
    0.55
    !!
    0.54
    AutoField
    0.54
     featuring
    0.53
    Activations Density 0.010%

    No Known Activations