© 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. 12-RES-MATRYOSHKA-DC
    7. 19276
    Prev
    Next
    INDEX
    Explanations

    references to classes or categories within a structured context

    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
     uğ
    -0.68
    RetentionPolicy
    -0.55
    BindingResult
    -0.53
    XmlType
    -0.53
     EdgeInsets
    -0.52
     ongles
    -0.49
    stalt
    -0.47
    if
    -0.46
    BeanUtils
    -0.45
    冲
    -0.45
    POSITIVE LOGITS
    classes
    1.14
     classes
    0.91
     Classes
    0.90
    Classes
    0.85
     disambiguazione
    0.82
     CLASSES
    0.76
    CLASSES
    0.63
     snippetHide
    0.63
    HasAnnotation
    0.63
    Portail
    0.60
    Activations Density 0.000%

    No Known Activations