© 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. 19866
    Prev
    Next
    INDEX
    Explanations

    terms related to components of electrical motors

    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
     Converse
    -0.75
     Sarko
    -0.74
    mess
    -0.68
     Ew
    -0.68
    Barr
    -0.63
    Mald
    -0.61
     Tada
    -0.61
     Mald
    -0.60
    Tes
    -0.60
    vän
    -0.59
    POSITIVE LOGITS
     rotor
    1.40
    Rotor
    1.19
     rotors
    1.18
    rotor
    1.18
     Rotor
    1.14
     Felton
    0.85
     Nieto
    0.84
     يتيمه
    0.79
     незавершена
    0.79
     AssemblyVersion
    0.77
    Activations Density 0.002%

    No Known Activations