© 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. 26501
    Prev
    Next
    INDEX
    Explanations

    references to "mass" or related terms in various contexts

    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
     InputDecoration
    -0.94
    ……"
    -0.92
     pinulongan
    -0.88
     Brakes
    -0.88
    ждую
    -0.88
    NameValuePair
    -0.87
     surla
    -0.86
    Datuak
    -0.84
     متعلقه
    -0.84
     hâte
    -0.84
    POSITIVE LOGITS
     Mas
    1.60
     mas
    1.43
    Mas
    1.32
    mas
    1.26
     Massey
    1.19
    MAS
    1.08
     MAS
    1.08
     Mascot
    0.86
     Mason
    0.84
    ymas
    0.78
    Activations Density 0.016%

    No Known Activations