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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 8621
    Prev
    Next
    INDEX
    Explanations

    the presence of specific tag-like or markup elements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.95
     AssemblyVersion
    -0.82
     Référence
    -0.82
     propOrder
    -0.78
     doInBackground
    -0.77
    principalTable
    -0.77
    rungsseite
    -0.74
    CodeAttribute
    -0.73
     consultato
    -0.71
     tartalomajánló
    -0.69
    POSITIVE LOGITS
     just
    0.57
     llev
    0.54
     з
    0.54
    ย
    0.54
     ت
    0.53
     déplacement
    0.52
     г
    0.51
     “
    0.50
     zd
    0.50
     Й
    0.50
    Activations Density 0.004%

    No Known Activations