© 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. 2-RES-MATRYOSHKA-DC
    7. 6572
    Prev
    Next
    INDEX
    Explanations

    sentences that explicitly state that "all" or "everything" is included or encompassed

    oai_token-act-pair · gpt-4.1-nano
    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
     estekak
    -0.96
    ]")]
    -0.93
    PerformLayout
    -0.91
    ResponseWriter
    -0.86
    \{\\
    -0.83
    ChildScrollView
    -0.82
    GraphicsUnit
    -0.82
     transfieras
    -0.82
     EconPapers
    -0.82
    AddTagHelper
    -0.81
    POSITIVE LOGITS
    abh
    0.46
    اق
    0.45
    ment
    0.44
    Int
    0.43
     All
    0.43
     Thumb
    0.43
     מע
    0.42
     whatsoever
    0.42
    pp
    0.40
    सं
    0.40
    Activations Density 0.007%

    No Known Activations