© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6415
    Prev
    Next
    INDEX
    Explanations

    key references to tables and figures in scientific documents

    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
    Sabah
    -0.43
     Woven
    -0.39
    likte
    -0.39
     sk
    -0.38
    faj
    -0.38
     Dirig
    -0.38
    нская
    -0.37
    +"/"+
    -0.36
    QC
    -0.36
    cite
    -0.36
    POSITIVE LOGITS
    хьтан
    1.08
     صوتيه
    1.07
    IUrlHelper
    0.96
     CreateTagHelper
    0.90
    HideFlags
    0.88
    ftagPool
    0.86
    providedIn
    0.85
     дописавши
    0.82
    makeConstraints
    0.81
    WriteTagHelper
    0.80
    Activations Density 0.052%

    No Known Activations