© 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. 1-CLT-HP
    7. 45831
    Prev
    Next
    INDEX
    Explanations

    parties and themed events

    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
    tagHelperRunner
    -0.79
     Roskov
    -0.77
     OMITBAD
    -0.74
    >{@
    -0.71
    ContextHolder
    -0.70
     vPvB
    -0.70
    ledem
    -0.68
     nahilalakip
    -0.66
    Хьажоргаш
    -0.66
    ResumeLayout
    -0.65
    POSITIVE LOGITS
     time
    0.54
    time
    0.52
     book
    0.47
    seg
    0.44
    book
    0.44
     mat
    0.43
    cube
    0.42
     day
    0.42
     walk
    0.42
     tale
    0.42
    Activations Density 0.039%

    No Known Activations