© 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. 12-RES-MATRYOSHKA-DC
    7. 4037
    Prev
    Next
    INDEX
    Explanations

    numeric data and formatting within the text

    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
     typelib
    -0.98
     nakalista
    -0.97
    BufferException
    -0.87
    +#+#
    -0.83
    SequentialGroup
    -0.82
    Билгалдахарш
    -0.81
    IsContent
    -0.80
    Демографія
    -0.80
    SharedDtor
    -0.79
     NSCoder
    -0.78
    POSITIVE LOGITS
    ве
    0.44
    ke
    0.43
    Reducer
    0.42
    kele
    0.41
    čas
    0.40
    ARD
    0.40
    Self
    0.40
     ronda
    0.39
    ard
    0.39
     biel
    0.39
    Activations Density 0.656%

    No Known Activations