© 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. 285
    Prev
    Next
    INDEX
    Explanations

    instances of strong emotional or impactful statements

    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
    ↵↵
    -0.56
    gameserver
    -0.53
    Furthermore
    -0.46
    Additionally
    -0.44
    También
    -0.43
    入
    -0.43
    ette
    -0.43
     presenti
    -0.42
     данный
    -0.42
     additionally
    -0.42
    POSITIVE LOGITS
    ReusableCell
    1.09
     autorytatywna
    0.86
    @[+][
    0.84
     مشين
    0.82
    يميديا
    0.82
     disambiguazione
    0.79
    MemoryWarning
    0.78
    存于互联网档案馆
    0.78
    Життєпис
    0.77
     zewnętrzne
    0.74
    Activations Density 1.504%

    No Known Activations