© 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. 31064
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or counts

    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
    NOPQRST
    -0.75
    verständlich
    -0.71
    oplasma
    -0.68
    dymyr
    -0.67
    PMailer
    -0.60
    resaid
    -0.58
    NTB
    -0.56
    esterday
    -0.55
    phylococcus
    -0.55
    imageshack
    -0.54
    POSITIVE LOGITS
    rungsseite
    0.82
    ⓧ
    0.78
    ècie
    0.69
    bag
    0.67
    Ona
    0.66
    sidemargin
    0.65
    Bag
    0.63
    SourceChecksum
    0.61
     Linton
    0.60
    pom
    0.60
    Activations Density 0.000%

    No Known Activations