© 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. 18-RES-MATRYOSHKA-DC
    7. 741
    Prev
    Next
    INDEX
    Explanations

    code snippets defining ports

    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.18.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.18.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
     telefónica
    -0.61
    UnknownFields
    -0.59
    ImageContext
    -0.56
    PerformLayout
    -0.53
     gynhyrchwyd
    -0.53
     nazionali
    -0.52
     '\\;'
    -0.52
     Pere
    -0.51
     télé
    -0.51
    ountain
    -0.51
    POSITIVE LOGITS
     port
    1.36
     Port
    1.15
     ports
    1.11
    Port
    1.11
    port
    1.02
     Ports
    1.02
     PORT
    0.98
    端口
    0.96
    PORT
    0.91
    ポート
    0.83
    Activations Density 0.446%

    No Known Activations