© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 29664
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific observations and measurements

    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
     betweenstory
    -1.14
     propOrder
    -0.99
     Vikipedi
    -0.96
     nakalista
    -0.91
    Hochspringen
    -0.90
    InjectAttribute
    -0.85
     صوتيه
    -0.85
    ⓧ
    -0.84
    AndEndTag
    -0.82
    SpringBootTest
    -0.81
    POSITIVE LOGITS
     or
    0.50
    ’
    0.47
    <eos>
    0.46
     is
    0.44
    ,
    0.43
    NSYLVANIA
    0.43
     the
    0.43
     and
    0.42
    CppMethod
    0.42
     very
    0.42
    Activations Density 0.450%

    No Known Activations