© 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. 11015
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or codes related to classifications

    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
     صوتيه
    -0.98
     typelib
    -0.85
    Portale
    -0.82
    EndContext
    -0.73
     Савезне
    -0.72
     المعيارى
    -0.71
     дописавши
    -0.66
    المشاركات
    -0.65
    principalTable
    -0.65
     Signalez
    -0.64
    POSITIVE LOGITS
    ريقيا
    0.54
     tanı
    0.48
    ①
    0.48
    深
    0.47
    </strong>
    0.46
    phic
    0.46
    ]<=
    0.45
    теристики
    0.45
    ффи
    0.45
     Kinect
    0.44
    Activations Density 0.001%

    No Known Activations