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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19923
    Prev
    Next
    INDEX
    Explanations

    references to implications in various contexts

    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
    TypedDataSet
    -1.13
    ftagPool
    -0.99
    ValueStyle
    -0.98
    GOTREF
    -0.84
    StructEnd
    -0.82
     виправивши
    -0.82
     propOrder
    -0.77
     createStore
    -0.76
    SourceChecksum
    -0.75
    moiselle
    -0.75
    POSITIVE LOGITS
     implications
    1.30
    Implications
    1.20
     Implications
    1.20
     IMPLICATIONS
    1.06
     ramifications
    0.97
    PLICATIONS
    0.94
     implication
    0.80
     implicated
    0.72
     implica
    0.69
     repercussions
    0.69
    Activations Density 0.004%

    No Known Activations