© 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. 3546
    Prev
    Next
    INDEX
    Explanations

    important scientific observations and findings

    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
     anyway
    -0.58
     anyways
    -0.50
    )))),
    -0.49
    ]:
    -0.48
    anyway
    -0.47
    vraagd
    -0.47
    ,:,
    -0.46
    ])));
    -0.46
    ngrx
    -0.45
    ebenarnya
    -0.44
    POSITIVE LOGITS
    出版年
    0.84
    sidemargin
    0.77
    labelledby
    0.71
    HostException
    0.65
    glBindTexture
    0.64
    AddTagHelper
    0.62
    rines
    0.60
    ToTensor
    0.60
     ANGELES
    0.58
    etcode
    0.57
    Activations Density 0.159%

    No Known Activations