© 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. 22931
    Prev
    Next
    INDEX
    Explanations

    expressions related to methods or approaches used in different contexts

    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
    aminen
    -0.52
     disqualified
    -0.51
     may
    -0.51
    DATABASES
    -0.50
    ↵↵
    -0.50
     sirop
    -0.49
     vinyle
    -0.49
     might
    -0.49
     would
    -0.48
     Szw
    -0.48
    POSITIVE LOGITS
    awtextra
    0.98
    Autoritní
    0.90
    MethodManager
    0.84
    onViewCreated
    0.78
    ########.
    0.76
    PerformLayout
    0.74
    LookAnd
    0.74
    estacks
    0.73
    UserScript
    0.73
    ftagPool
    0.70
    Activations Density 0.011%

    No Known Activations