© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4737
    Prev
    Next
    INDEX
    Explanations

    comparative phrases related to values and their relationships

    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
    ,
    -0.52
     S
    -0.51
     s
    -0.49
     de
    -0.46
    :
    -0.43
     del
    -0.43
     major
    -0.42
    間
    -0.42
    sto
    -0.42
     кое
    -0.42
    POSITIVE LOGITS
     Roskov
    1.16
     Мексичка
    1.14
     للمعارف
    1.07
    CppMethod
    1.00
    IntoConstraints
    1.00
    NameInMap
    0.92
     pinulongan
    0.91
     يتيمه
    0.90
     nahilalakip
    0.89
     &___
    0.89
    Activations Density 0.043%

    No Known Activations