© 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. 19330
    Prev
    Next
    INDEX
    Explanations

    phrases that involve the word "for" and its various uses

    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
     bagi
    -0.83
     for
    -0.71
    তথ্যসূত্র
    -0.66
    forKey
    -0.60
    Bagi
    -0.59
     anyone
    -0.58
    for
    -0.57
     voor
    -0.56
     jScrollPane
    -0.56
     Bagi
    -0.55
    POSITIVE LOGITS
    ersburg
    0.72
    extAlignment
    0.71
    asInstanceOf
    0.69
    cticas
    0.67
     föld
    0.67
     Penh
    0.65
    useEffect
    0.64
    cely
    0.64
     klart
    0.64
    Begriffsklä
    0.62
    Activations Density 0.020%

    No Known Activations