© 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. 18-RES-MATRYOSHKA-DC
    7. 1050
    Prev
    Next
    INDEX
    Explanations

    mentions of a study's findings and the influence or roles things play within them

    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.18.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.18.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
    Diweddarwch
    -0.75
     disambiguazione
    -0.67
    ImageContext
    -0.65
    transQ
    -0.65
    DebuggerNonUser
    -0.64
    rrggbb
    -0.64
     förr
    -0.63
    NameInMap
    -0.63
    webElement
    -0.62
    ValueStyle
    -0.59
    POSITIVE LOGITS
    setVerticalGroup
    0.73
    VersionUID
    0.61
    RunAsync
    0.52
    ppins
    0.49
    abstractmethod
    0.48
    SourceChecksum
    0.46
    ExtendWith
    0.45
    xDB
    0.43
     peran
    0.43
    dington
    0.42
    Activations Density 0.408%

    No Known Activations