© 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. 10928
    Prev
    Next
    INDEX
    Explanations

    references to specific titles and tags associated with content

    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
    นี้
    -0.57
    новниш
    -0.54
    verlag
    -0.52
    čius
    -0.50
    moy
    -0.50
     lại
    -0.49
     "$
    -0.49
     Idris
    -0.47
    ショナル
    -0.47
    nbsp
    -0.47
    POSITIVE LOGITS
     Efq
    0.69
     myſelf
    0.68
     varandra
    0.68
    kenstock
    0.67
    SPATH
    0.65
     feroit
    0.65
     réguli
    0.62
     auroit
    0.62
     dépens
    0.61
     déchir
    0.60
    Activations Density 0.344%

    No Known Activations