© 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. 0-CLT-HP
    7. 45557
    Prev
    Next
    INDEX
    Explanations

    endoc

    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
     endocrine
    -0.59
     honey
    -0.58
     hone
    -0.57
     brothers
    -0.52
     Empress
    -0.52
    vací
    -0.51
     endoc
    -0.51
     Hone
    -0.50
     talk
    -0.47
    ization
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.87
    StoryboardSegue
    0.74
    elemField
    0.73
    GEBURTSDATUM
    0.73
     estekak
    0.68
    sizeCache
    0.66
    </caption>
    0.66
    SPATH
    0.66
     ostavi
    0.65
    principalTable
    0.64
    Activations Density 2.091%

    No Known Activations