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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 31674
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical statistics or data points within the document

    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
     дописавши
    -0.71
    InjectAttribute
    -0.68
    ImageContext
    -0.67
     <>",
    -0.67
    CloseOperation
    -0.63
     mangrove
    -0.63
    +#+#
    -0.62
    phosa
    -0.61
    Демографія
    -0.60
     odkazy
    -0.60
    POSITIVE LOGITS
    SequentialGroup
    0.52
    DIPSETTING
    0.46
    帖最后由
    0.46
    mso
    0.44
    لا
    0.41
    ly
    0.41
    ?}",
    0.39
    )?;
    0.39
    verifyException
    0.39
     Kassen
    0.38
    Activations Density 0.044%

    No Known Activations