© 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. 32182
    Prev
    Next
    INDEX
    Explanations

    quantitative or statistical data presented as figures or measurements

    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
    來說
    -0.58
    awtextra
    -0.56
    来说
    -0.52
    exels
    -0.51
    ValueStyle
    -0.49
    আ
    -0.43
    uolo
    -0.40
    amela
    -0.39
    amse
    -0.39
    tech
    -0.39
    POSITIVE LOGITS
     AssemblyCulture
    0.82
    uxxxx
    0.71
    __':
    0.69
     oprot
    0.68
    исленность
    0.66
    ItemBackground
    0.66
    StructEnd
    0.65
    clusal
    0.65
    
    0.65
     UIAlert
    0.65
    Activations Density 0.021%

    No Known Activations