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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 38
    Prev
    Next
    INDEX
    Explanations

    sequences of underscore characters or formatting tokens

    oai_token-act-pair · gpt-4.1-nano
    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
    StoryboardSegue
    -1.04
     없습니다
    -0.82
     tartalomajánló
    -0.81
    HasForeignKey
    -0.81
    NameInMap
    -0.78
     doInBackground
    -0.78
     viewType
    -0.77
     ExecuteAsync
    -0.77
    )"),
    -0.76
    getOutputStream
    -0.76
    POSITIVE LOGITS
    _
    2.25
    \_
    1.52
     _
    1.13
    //_
    1.13
    +"_
    1.02
     "_
    1.00
    }_
    0.96
    )_
    0.95
    _"
    0.95
    _-_
    0.94
    Activations Density 4.890%

    No Known Activations