© 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. 14341
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reasons or justifications

    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
     Why
    -0.62
    Why
    -0.59
     createContext
    -0.58
     encom
    -0.56
     WHY
    -0.55
    olyn
    -0.54
     Doria
    -0.54
     CYTHON
    -0.54
    MODO
    -0.53
    How
    -0.52
    POSITIVE LOGITS
    WebVitals
    0.86
    WriteBarrier
    0.76
    VersionUID
    0.74
    \{\\
    0.73
    DotNetBar
    0.70
     Roskov
    0.70
     kasarigan
    0.68
     оригіналу
    0.68
     NavController
    0.67
    XmlAccessorType
    0.65
    Activations Density 0.015%

    No Known Activations