© 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. 18445
    Prev
    Next
    INDEX
    Explanations

    terms related to data storage or memory management

    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
     pleaſure
    -1.22
     itſelf
    -1.18
     laiton
    -1.15
     fhew
    -1.13
     Majefty
    -1.13
     Monfieur
    -1.12
     ſtate
    -1.08
     themſelves
    -1.06
     împre
    -1.04
     piú
    -1.04
    POSITIVE LOGITS
    STORAGE
    0.97
     
    0.89
    getStorage
    0.85
     Storage
    0.84
    Storage
    0.82
     am
    0.77
    <sup>
    0.73
     I
    0.72
    storage
    0.71
     storage
    0.70
    Activations Density 0.020%

    No Known Activations