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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3900
    Prev
    Next
    INDEX
    Explanations

    concerns related to preventing accidents and damage

    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
     precept
    -0.53
    Totale
    -0.50
    囗
    -0.49
    almost
    -0.48
     gemeenten
    -0.48
     almost
    -0.47
     mayors
    -0.47
     litté
    -0.47
     tunnels
    -0.46
    Almost
    -0.44
    POSITIVE LOGITS
     مرئيه
    0.88
    DockStyle
    0.78
    /**
    0.69
     Normdatei
    0.63
     "..\..\..\
    0.61
    ไหน
    0.60
    发表于
    0.59
     futuros
    0.59
     artikkelen
    0.59
    igny
    0.57
    Activations Density 0.382%

    No Known Activations