© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39788
    Prev
    Next
    INDEX
    Explanations

    loops

    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
     Loop
    -0.64
     loop
    -0.64
     looping
    -0.63
    Loop
    -0.56
     looped
    -0.55
    ondheim
    -0.54
    GEBURTS
    -0.54
    ariki
    -0.54
    loop
    -0.53
     وتسجيلات
    -0.53
    POSITIVE LOGITS
     autorytatywna
    0.80
    Personendaten
    0.66
    RuleContext
    0.64
    IVEREF
    0.58
    Przypisy
    0.57
     dovuto
    0.54
     mergeFrom
    0.50
     useStyles
    0.48
     WER
    0.48
     ailes
    0.47
    Activations Density 0.163%

    No Known Activations