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. 8662
    Prev
    Next
    INDEX
    Explanations

    phrases related to competing interests in research

    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
    SharedDtor
    -0.96
    onAttach
    -0.79
    rungsseite
    -0.78
    MLLoader
    -0.75
     Roskov
    -0.73
    цездатний
    -0.71
    SourceChecksum
    -0.71
     iprot
    -0.71
    kuuta
    -0.68
    EndGlobalSection
    -0.68
    POSITIVE LOGITS
    зде
    0.54
     construed
    0.49
     prior
    0.46
    cshtml
    0.46
     논
    0.41
     artikkelen
    0.40
    tungen
    0.40
     fitting
    0.39
    企
    0.39
     suggesting
    0.39
    Activations Density 0.001%

    No Known Activations