© 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. 5263
    Prev
    Next
    INDEX
    Explanations

    references to receiving or getting something

    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
     חיצוניים
    -0.81
    لينكات
    -0.75
     calendriers
    -0.74
     kohdetta
    -0.73
    onAttach
    -0.73
    glä
    -0.73
    onucleotide
    -0.71
    طة
    -0.69
    ostro
    -0.68
    ainte
    -0.68
    POSITIVE LOGITS
     Receive
    1.39
     RECEIVE
    1.37
     received
    1.35
     RECE
    1.35
     receive
    1.33
     recieved
    1.30
     Receiving
    1.28
     Rece
    1.27
    received
    1.27
    Rece
    1.27
    Activations Density 0.280%

    No Known Activations