© 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. 16778
    Prev
    Next
    INDEX
    Explanations

    greetings or friendly interactions

    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
    lapia
    -0.44
    esez
    -0.43
    Discography
    -0.42
     segü
    -0.41
     most
    -0.41
    VIER
    -0.40
    orsese
    -0.40
    /*-
    -0.40
    تقاوى
    -0.40
    nost
    -0.39
    POSITIVE LOGITS
    istoitu
    0.85
     الرياضيه
    0.76
     OFDb
    0.76
    WebControls
    0.74
    webElementGuid
    0.72
    MemoryWarning
    0.71
    исленность
    0.71
    indd
    0.69
    EndProject
    0.66
    InjectAttribute
    0.66
    Activations Density 0.023%

    No Known Activations