© 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. 1689
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to progress or movement in a particular direction

    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
    POSE
    -0.54
    фраструк
    -0.51
     boven
    -0.51
    apimachinery
    -0.51
     HasFactory
    -0.47
    elyn
    -0.46
     dalamnya
    -0.46
     samband
    -0.46
    ENSES
    -0.45
    "}")
    -0.45
    POSITIVE LOGITS
     towards
    2.92
     toward
    2.86
    toward
    2.59
    towards
    2.59
     Towards
    2.52
     Toward
    2.45
    Towards
    2.30
    Toward
    2.19
     hacia
    1.95
     TOW
    1.85
    Activations Density 0.749%

    No Known Activations