© 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. 2179
    Prev
    Next
    INDEX
    Explanations

    references to different approaches or methodologies

    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
    Mur
    -0.65
     Mur
    -0.65
    quot
    -0.65
     Rosenberg
    -0.64
     McCoy
    -0.60
     Nite
    -0.60
    enumerate
    -0.60
    ークル
    -0.60
     tys
    -0.59
     Hickey
    -0.58
    POSITIVE LOGITS
     approaches
    1.59
     Approaches
    1.54
     APPROACH
    1.48
     Approach
    1.48
    Approach
    1.42
     approach
    1.31
    approach
    1.23
    Appro
    1.18
     approached
    1.13
     approaching
    1.03
    Activations Density 0.042%

    No Known Activations