© 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. 1485
    Prev
    Next
    INDEX
    Explanations

    phrases referencing specific conditions or parameters within a defined scope or framework

    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
     Pattaya
    -0.74
    er
    -0.69
    SupportActionBar
    -0.69
     deswegen
    -0.65
     Dalio
    -0.65
    ardı
    -0.65
     TPS
    -0.65
     Paola
    -0.63
     Gerber
    -0.63
     Lawler
    -0.63
    POSITIVE LOGITS
    within
    1.72
     Within
    1.67
     within
    1.64
    Within
    1.64
     WITHIN
    1.52
     dentro
    1.15
     entro
    1.15
     binnen
    1.14
    dentro
    1.13
     innerhalb
    1.08
    Activations Density 0.328%

    No Known Activations