© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 412
    Prev
    Next
    INDEX
    Explanations

    sections of text that discuss initial conditions or introductory contexts

    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
    ритори
    -0.59
     دیکھیے
    -0.55
    demie
    -0.53
    ائب
    -0.52
    AGRAM
    -0.48
    хин
    -0.46
    PyExc
    -0.46
    allax
    -0.46
     co
    -0.46
     brazo
    -0.45
    POSITIVE LOGITS
     inicial
    1.24
    INITIAL
    1.13
     initial
    1.12
    unächst
    1.11
     awal
    1.09
     iniziale
    1.09
    initial
    1.09
    Initial
    1.08
     INITIAL
    1.08
     Initial
    1.06
    Activations Density 3.042%

    No Known Activations