© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1155
    Prev
    Next
    INDEX
    Explanations

    statistical comparisons

    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.22.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.22.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
     (\%)
    -0.62
    ndre
    -0.51
     (\%
    -0.50
     (%)
    -0.50
     متعلقه
    -0.48
     ferons
    -0.47
    ADATA
    -0.46
    berton
    -0.45
     reprises
    -0.45
     $(\%)$
    -0.45
    POSITIVE LOGITS
     p
    1.09
    SequentialGroup
    0.89
    p
    0.81
     P
    0.79
    ValueStyle
    0.76
    Xna
    0.70
    ｐ
    0.64
    P
    0.60
     GenerationType
    0.60
    ConstraintMaker
    0.59
    Activations Density 0.596%

    No Known Activations