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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11162
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "oracle."

    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
    rungsseite
    -0.71
    bewerken
    -0.66
    Personensuche
    -0.61
    허
    -0.60
     noDo
    -0.60
     betweenstory
    -0.59
    ṁ
    -0.58
    balleur
    -0.57
    parsedMessage
    -0.57
    تقاوى
    -0.57
    POSITIVE LOGITS
    oracle
    2.05
     oracle
    1.09
    Oracle
    0.92
     Oracle
    0.90
     oracles
    0.61
    netbeans
    0.59
     Thebes
    0.59
    tweets
    0.58
    UserGroup
    0.58
    deaux
    0.56
    Activations Density 0.000%

    No Known Activations