© 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. 1849
    Prev
    Next
    INDEX
    Explanations

    hyperlinks in 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
     Stepan
    -0.84
     nahilalakip
    -0.80
     maso
    -0.73
     Lando
    -0.73
    :✨
    -0.73
    rungsseite
    -0.73
     Yad
    -0.72
     Chaldean
    -0.71
     Arjuna
    -0.71
     Volker
    -0.69
    POSITIVE LOGITS
     href
    1.59
    href
    1.05
    Href
    0.90
    GHIJKLM
    0.64
     cref
    0.62
     the
    0.59
    BeginContext
    0.53
    Sziasztok
    0.52
     محفوظة
    0.51
     terus
    0.50
    Activations Density 0.030%

    No Known Activations