© 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. 18-RES-MATRYOSHKA-DC
    7. 1308
    Prev
    Next
    INDEX
    Explanations

    scientific publications and references

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    MessageTagHelper
    -0.61
     AttributeSet
    -0.57
     برانيه
    -0.54
    mtrl
    -0.52
    aarrggbb
    -0.52
    OneToMany
    -0.52
    رامج
    -0.50
     مخطط
    -0.50
    voort
    -0.50
     surla
    -0.49
    POSITIVE LOGITS
     publication
    1.41
     publications
    1.23
     paper
    1.23
     publishing
    1.20
     papers
    1.18
     publish
    1.17
     journal
    1.15
     published
    1.15
     journals
    1.12
     authors
    1.09
    Activations Density 2.620%

    No Known Activations