© 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. 10845
    Prev
    Next
    INDEX
    Explanations

    terms related to manipulation or control actions

    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
    ings
    -0.75
    a
    -0.64
    gulier
    -0.63
     Zephyr
    -0.61
    board
    -0.61
    boards
    -0.61
     Brod
    -0.61
    fi
    -0.60
    ———
    -0.59
     ruban
    -0.59
    POSITIVE LOGITS
     Manip
    1.62
     manipulate
    1.55
    manip
    1.52
    Manip
    1.45
     manip
    1.44
     manipulator
    1.39
     manipulations
    1.35
     Manipulation
    1.34
     manipulated
    1.34
     manipulation
    1.33
    Activations Density 0.004%

    No Known Activations