Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30110
    Prev
    Next
    INDEX
    Explanations

    code with syntax characters and specific punctuation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.92
    abetes
    -0.69
    writerow
    -0.67
    ioutil
    -0.61
    classnames
    -0.61
    かれています
    -0.61
    endaft
    -0.60
    RetentionPolicy
    -0.59
    vereignty
    -0.59
    Literatuur
    -0.59
    POSITIVE LOGITS
     House
    0.61
      
    0.61
    ↵↵
    0.60
     betweenstory
    0.59
    脚注の使い方
    0.56
     distanciation
    0.53
    })
    0.53
     )
    0.52
    <bos>
    0.52
    ftagPool
    0.52
    Activations Density 0.125%

    No Known Activations