© 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. 14012
    Prev
    Next
    INDEX
    Explanations

    versioning or identification numbers related to an API

    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
    oredCriteria
    -0.68
    tvguidetime
    -0.65
     )}$
    -0.58
    onAttach
    -0.57
    liyor
    -0.56
    ypep
    -0.56
     propOrder
    -0.56
    abestanden
    -0.55
     مشين
    -0.54
    viewDidLoad
    -0.54
    POSITIVE LOGITS
    iastes
    0.54
    unsqueeze
    0.51
    DllImport
    0.47
    Portale
    0.45
    انجليز
    0.45
    ilah
    0.45
    paka
    0.44
     ARMS
    0.43
     ligiloj
    0.42
    Rüyada
    0.42
    Activations Density 0.003%

    No Known Activations