© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19677
    Prev
    Next
    INDEX
    Explanations

    business-related terms and their contextual usage

    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
     only
    -0.84
     onely
    -0.76
    only
    -0.68
     лишь
    -0.66
    Only
    -0.65
    ########.
    -0.64
    SBATCH
    -0.64
     Only
    -0.63
    Apenas
    -0.59
     ONLY
    -0.59
    POSITIVE LOGITS
    damit
    0.54
    Fig
    0.53
    UrlResolution
    0.53
    ✨:
    0.52
    ahuila
    0.52
     Meksiku
    0.51
    olymers
    0.51
    дә
    0.51
    liesslich
    0.49
    Nouveau
    0.49
    Activations Density 0.022%

    No Known Activations