© 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. 19993
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "pre" 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
     '\\;'
    -0.83
     Wallflower
    -0.82
    UnknownFields
    -0.81
    Personendaten
    -0.81
     bouch
    -0.79
    ready
    -0.78
     Ready
    -0.77
     utafitiHapana
    -0.77
     nakalista
    -0.76
    preparing
    -0.76
    POSITIVE LOGITS
    Pre
    1.13
     Pre
    1.06
    PRE
    1.03
     PRE
    1.03
    pre
    0.94
     pre
    0.87
     Prem
    0.71
     Pref
    0.69
     Morena
    0.66
     Preacher
    0.66
    Activations Density 0.027%

    No Known Activations