© 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. 29896
    Prev
    Next
    INDEX
    Explanations

    legal citations and references

    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
     EconPapers
    -0.91
    ftagPool
    -0.89
     المعيارى
    -0.81
    +#+
    -0.76
    脚注の使い方
    -0.76
    RenderAtEndOf
    -0.76
    intios
    -0.75
    Tikang
    -0.74
    OGND
    -0.73
     himo
    -0.73
    POSITIVE LOGITS
     Nig
    0.58
     totalSupply
    0.54
    ly
    0.52
    索
    0.49
    ry
    0.48
    ro
    0.46
    ss
    0.46
     Ross
    0.46
    zz
    0.46
    li
    0.44
    Activations Density 0.020%

    No Known Activations