© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16615
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "in."

    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
    addPreferredGap
    -0.56
     externi
    -0.54
     a
    -0.52
     Co
    -0.52
     common
    -0.52
    lassified
    -0.47
    FIL
    -0.45
     Tap
    -0.45
    ->_
    -0.44
    Kariera
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.85
     wireType
    0.83
    #+#
    0.82
    ].)
    0.79
    ExtendWith
    0.76
    WebServlet
    0.75
    '}>
    0.75
     Signalez
    0.74
     Romagna
    0.74
    MigrationBuilder
    0.72
    Activations Density 0.018%

    No Known Activations