© 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. 1668
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "long" 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
    Datuak
    -1.25
     AssemblyVersion
    -1.08
     myſelf
    -1.07
    GEBURTSDATUM
    -1.06
    ieteur
    -1.05
    queryInterface
    -1.03
    BibitemShut
    -0.97
     Monfieur
    -0.96
    tonode
    -0.95
    ValueStyle
    -0.93
    POSITIVE LOGITS
     Long
    1.48
    long
    1.48
    Long
    1.48
     long
    1.44
     LONG
    1.43
    LONG
    1.31
    getLong
    1.28
     length
    1.27
    length
    1.23
     longest
    1.22
    Activations Density 0.526%

    No Known Activations