Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19741
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, specifically terms related to matrices and functions in mathematical expressions

    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
    </tfoot>
    -0.70
     переписи
    -0.69
    GEBURTS
    -0.66
    WriteLiteral
    -0.65
    Derbyniad
    -0.63
    basicConfig
    -0.61
    RegressionTest
    -0.60
     OFDb
    -0.60
    setVerticalGroup
    -0.58
     rappeler
    -0.57
    POSITIVE LOGITS
    Initializable
    0.50
    ựa
    0.49
    alter
    0.48
    пол
    0.47
     alter
    0.46
     getopt
    0.46
    󠁣
    0.46
     rospy
    0.43
     obs
    0.43
     чер
    0.43
    Activations Density 0.015%

    No Known Activations