© 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. 24695
    Prev
    Next
    INDEX
    Explanations

    underscore-prefixed variables or functions in code

    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
     Signalez
    -0.94
    AddTagHelper
    -0.89
     []:
    -0.82
    Personendaten
    -0.81
    PageContext
    -0.79
    StoryboardSegue
    -0.79
     Roskov
    -0.79
    RenderAtEndOf
    -0.78
     saites
    -0.77
     NSCoder
    -0.77
    POSITIVE LOGITS
     Maury
    0.47
     possibilidades
    0.47
    get
    0.44
    omba
    0.43
     digitais
    0.43
     району
    0.43
    est
    0.43
    aura
    0.43
    Історія
    0.42
     Tompkins
    0.42
    Activations Density 0.133%

    No Known Activations