© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15907
    Prev
    Next
    INDEX
    Explanations

    software licensing terms and conditions

    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
    Negative Logits
    LICENSE
    -1.23
    RegressionTest
    -0.93
     Efq
    -0.89
     myſelf
    -0.85
     Monfieur
    -0.85
     Theſe
    -0.84
     ſeveral
    -0.82
     Chrift
    -0.81
     Majefty
    -0.81
     themſelves
    -0.80
    POSITIVE LOGITS
    >-->
    0.44
    irah
    0.42
     with
    0.42
     within
    0.42
     res
    0.41
    cshtml
    0.40
     Sch
    0.39
    MENAFN
    0.39
     da
    0.38
    PRNewswire
    0.38
    Activations Density 0.002%

    No Known Activations