© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20
    Prev
    Next
    INDEX
    Explanations

    strings or identifiers that appear to be related to coding, likely referencing variables or data types

    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
    setVerticalGroup
    -1.27
     autorytatywna
    -1.16
     tartalomajánló
    -1.10
    EndGlobalSection
    -1.09
    存于互联网档案馆
    -1.06
     كومونز
    -1.05
     дописавши
    -1.05
     initComponents
    -1.05
     bezeichneter
    -1.05
     Audiodateien
    -1.04
    POSITIVE LOGITS
    7
    0.65
    3
    0.63
    .
    0.62
    4
    0.61
    9
    0.61
    8
    0.61
    1
    0.60
    2
    0.60
    6
    0.59
    ↵↵↵
    0.59
    Activations Density 3.492%

    No Known Activations