© 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. 25544
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and scientific protocol details

    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
    typeparam
    -0.59
    __":
    -0.51
     вид
    -0.49
    IBase
    -0.49
    DDG
    -0.49
    inete
    -0.46
    __':
    -0.46
    adă
    -0.46
    ADL
    -0.46
    الإنجليزية
    -0.45
    POSITIVE LOGITS
    Personensuche
    0.81
    BeginContext
    0.66
     Normdatei
    0.66
     ſever
    0.63
     firſt
    0.60
     désolés
    0.59
     ſtill
    0.58
     liquidation
    0.57
     Liquid
    0.56
     greateſt
    0.56
    Activations Density 0.059%

    No Known Activations