© 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. 22-RES-MATRYOSHKA-DC
    7. 2493
    Prev
    Next
    INDEX
    Explanations

    code block headers in multiple coding languages

    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
    $\
    -0.54
    $
    -0.54
    </i>
    -0.50
    =(\
    -0.49
    lijkse
    -0.47
    $=\
    -0.45
    “
    -0.45
    !’
    -0.44
    ő
    -0.42
    ltä
    -0.42
    POSITIVE LOGITS
    /**
    1.89
     /**
    1.27
    /**
    1.27
    /**
    1.05
    /**
    1.01
    ///**
    0.98
     «
    0.92
    -/**
    0.90
     surla
    0.89
     /**
    0.85
    Activations Density 0.041%

    No Known Activations