© 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. 16640
    Prev
    Next
    INDEX
    Explanations

    quantifiable data related to incidents, victims, and statistical analysis

    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
     ComVisible
    -0.44
     kasarigan
    -0.43
    </em>
    -0.39
     saw
    -0.38
    Kemudian
    -0.38
    Activité
    -0.37
    vės
    -0.37
    ьажоргаш
    -0.36
    ActionCreators
    -0.36
    Reprints
    -0.36
    POSITIVE LOGITS
    ">//
    0.89
    RepeatedField
    0.81
    +#+#
    0.79
    __":
    0.74
    CodedInputStream
    0.74
    IUrlHelper
    0.73
     initComponents
    0.71
    ValueStyle
    0.71
     considérons
    0.71
    IsMutable
    0.71
    Activations Density 0.125%

    No Known Activations