© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19808
    Prev
    Next
    INDEX
    Explanations

    concepts related to cognitive functions and skills necessary for effective learning and critical thinking

    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
    GEBURTSDATUM
    -0.76
     EconPapers
    -0.65
    onAttach
    -0.63
    fromnode
    -0.60
    inSlope
    -0.58
    RenderAtEndOf
    -0.58
     Rudi
    -0.57
    <>());
    -0.57
    richTextPanel
    -0.57
    setopt
    -0.56
    POSITIVE LOGITS
    Advertisement
    0.50
     creatividad
    0.48
    รร
    0.47
     Problem
    0.47
    UnitTesting
    0.47
     originality
    0.46
     executive
    0.45
     Wayback
    0.45
    SequentialGroup
    0.45
     discernment
    0.44
    Activations Density 0.093%

    No Known Activations