© 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. 30162
    Prev
    Next
    INDEX
    Explanations

    the word "necessarily" 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
    !*\
    -0.84
    paravant
    -0.80
    CACHE
    -0.65
    atzung
    -0.65
     intptr
    -0.63
    发表于
    -0.63
    Tembelea
    -0.62
     desertion
    -0.62
     Ull
    -0.61
    linien
    -0.60
    POSITIVE LOGITS
    UnusedPrivate
    0.72
     considérons
    0.65
    >`;
    0.64
    DrawerToggle
    0.64
    колко
    0.63
    PyExc
    0.62
    parsedMessage
    0.62
    addCriterion
    0.61
    +#+#
    0.61
    EndGlobalSection
    0.60
    Activations Density 0.005%

    No Known Activations