© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19157
    Prev
    Next
    INDEX
    Explanations

    conjunctions used to create compound phrases

    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
    WriteTagHelper
    -1.13
     صوتيه
    -1.01
    SourceChecksum
    -0.92
     ModelExpression
    -0.89
    WebElementEntity
    -0.89
    </thead>
    -0.87
     Majefty
    -0.87
    OGND
    -0.85
     poffe
    -0.85
     raiſ
    -0.84
    POSITIVE LOGITS
     [*]
    0.59
    IBarButtonItem
    0.52
     gagner
    0.46
    KeyId
    0.46
    Extent
    0.45
    står
    0.45
    greenrobot
    0.45
    неопр
    0.43
     skj
    0.43
     rubrique
    0.42
    Activations Density 0.033%

    No Known Activations