© 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. 8730
    Prev
    Next
    INDEX
    Explanations

    references to the piano and pianists

    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
     gorro
    -0.68
    RSpec
    -0.68
     protoimpl
    -0.66
    ')(
    -0.63
    repr
    -0.63
     Moq
    -0.62
     Cuth
    -0.60
     frattempo
    -0.60
    Détails
    -0.59
    sourced
    -0.59
    POSITIVE LOGITS
     Piano
    1.70
    Piano
    1.66
     pianos
    1.64
     piano
    1.59
     PIANO
    1.53
    piano
    1.38
     pianist
    1.13
     pian
    1.10
     Pian
    1.10
    Pian
    1.08
    Activations Density 0.001%

    No Known Activations