Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 32215
    Prev
    Next
    INDEX
    Explanations

    URLs and web links in the text

    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
     consultato
    -0.58
    MigrationBuilder
    -0.47
     vapa
    -0.46
    ModelAdmin
    -0.46
     年代
    -0.46
    Inset
    -0.46
    addPreferredGap
    -0.45
    Bonjour
    -0.45
    BBBB
    -0.44
     Aurelius
    -0.43
    POSITIVE LOGITS
     autorytatywna
    0.71
    хьтан
    0.70
    сылкі
    0.69
    AddTagHelper
    0.65
    ftagPool
    0.65
    ttps
    0.64
     gynhyrchwyd
    0.63
    Hentet
    0.61
     How
    0.59
     المعيارى
    0.59
    Activations Density 0.034%

    No Known Activations