© 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. 26610
    Prev
    Next
    INDEX
    Explanations

    details about references and citations in academic texts

    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
     >=",
    -0.68
     pleaſure
    -0.62
    esez
    -0.58
    /**
    -0.55
     transférez
    -0.53
     anzuzeigen
    -0.52
     AssemblyTitle
    -0.51
     Turquie
    -0.51
     translateY
    -0.51
    θυ
    -0.51
    POSITIVE LOGITS
    ResumeLayout
    0.68
    出版年
    0.60
    RegressionTest
    0.59
    WindowConstants
    0.56
    queryInterface
    0.55
    KURZBESCHREIBUNG
    0.54
    printStackTrace
    0.52
    GetEnumerator
    0.52
    ########.
    0.50
    devise
    0.49
    Activations Density 0.005%

    No Known Activations