© 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. 6-RES-MATRYOSHKA-DC
    7. 1161
    Prev
    Next
    INDEX
    Explanations

    the word "target", often followed by "framework"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CBA
    -0.62
     FLOW
    -0.59
    writing
    -0.59
    libri
    -0.57
     fistula
    -0.57
    xffffff
    -0.55
     Jaz
    -0.54
     CBA
    -0.54
      
    -0.54
     skrive
    -0.54
    POSITIVE LOGITS
     targets
    2.41
     target
    2.30
     Targets
    2.20
     Target
    2.16
     TARGET
    2.16
    TARGET
    2.11
     cible
    2.11
    target
    2.06
    targets
    2.06
    Target
    2.02
    Activations Density 0.480%

    No Known Activations