© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 523
    Prev
    Next
    INDEX
    Explanations

    java import statements and package declarations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     trasparente
    -0.69
     iniziale
    -0.50
     professionale
    -0.50
     dår
    -0.49
     seguente
    -0.49
     vandens
    -0.48
     putea
    -0.47
     smě
    -0.47
     storica
    -0.47
    Iden
    -0.46
    POSITIVE LOGITS
     org
    0.85
    ]")]
    0.82
    \{\\
    0.77
     com
    0.77
     Савезне
    0.74
    ")));
    0.72
    __(/*!
    0.71
    Datuak
    0.70
    endphp
    0.69
    bibinfo
    0.67
    Activations Density 0.223%

    No Known Activations