© 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. 4-CLT-HP
    7. 4398
    Prev
    Next
    INDEX
    Explanations

    repeating words

    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
    脚注の使い方
    -0.73
    Obrázky
    -0.60
    oa̍t
    -0.55
     ASX
    -0.55
    TypedDataSet
    -0.52
     echoed
    -0.50
    MRP
    -0.49
     echoing
    -0.49
     Numerade
    -0.49
    endpush
    -0.48
    POSITIVE LOGITS
    новништво
    0.63
     consultato
    0.59
    ément
    0.54
     '{@
    0.54
    staat
    0.53
    Sekarang
    0.52
    printStackTrace
    0.51
    Else
    0.51
    lotte
    0.51
     numberOfRows
    0.50
    Activations Density 0.006%

    No Known Activations