© 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. 1930
    Prev
    Next
    INDEX
    Explanations

    references to a concept of "target" 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
    CBA
    -0.74
    xffffff
    -0.66
     Jaz
    -0.65
     ProgressDialog
    -0.65
     CBA
    -0.63
     FLOW
    -0.61
     multer
    -0.58
     colitis
    -0.58
     psycopg
    -0.58
     dysplasia
    -0.58
    POSITIVE LOGITS
     targets
    1.89
     Targets
    1.72
     TARGET
    1.70
     target
    1.67
     Target
    1.66
    TARGET
    1.64
    targets
    1.62
     cible
    1.49
    Target
    1.48
    target
    1.47
    Activations Density 0.114%

    No Known Activations