© 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. 1373
    Prev
    Next
    INDEX
    Explanations

    terms related to technical and scientific processes

    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
     calendriers
    -0.74
     thiệu
    -0.68
    hyrchwyd
    -0.66
    rungsseite
    -0.64
     विश्वसनीयता
    -0.59
    tagHelperRunner
    -0.59
     utafitiHapana
    -0.57
    Karriere
    -0.56
    Географиясе
    -0.56
    PerformLayout
    -0.55
    POSITIVE LOGITS
     markers
    0.60
    ::::::::
    0.54
     ThemeData
    0.54
     Shakspeare
    0.53
     ARXIV
    0.52
     Gson
    0.51
     Roskov
    0.50
    olesale
    0.49
     CoreData
    0.49
    ngOn
    0.48
    Activations Density 1.593%

    No Known Activations