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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11364
    Prev
    Next
    INDEX
    Explanations

    discussions around flaws and vulnerabilities in systems or arguments

    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
    ⓧ
    -0.65
    InputElement
    -0.56
     consultato
    -0.52
    DrawerToggle
    -0.50
    /**
    -0.48
    ANES
    -0.46
     hervor
    -0.46
     ↓,
    -0.46
    Sesion
    -0.46
     Мексичка
    -0.45
    POSITIVE LOGITS
    SharedCtor
    0.67
    enterOuterAlt
    0.61
    HomeAsUpEnabled
    0.60
     dentaire
    0.60
     Landsat
    0.58
    seamnă
    0.58
     juridiques
    0.57
    шкан
    0.57
     ovary
    0.56
     elettrica
    0.55
    Activations Density 0.020%

    No Known Activations