© 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. 15543
    Prev
    Next
    INDEX
    Explanations

    negations and negative expressions

    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
     AssemblyTitle
    -0.96
    tfrac
    -0.94
    BeginContext
    -0.92
    RegressionTest
    -0.91
    \{\\
    -0.90
    ThroughAttribute
    -0.90
     Exacts
    -0.89
    InlineData
    -0.88
    Obras
    -0.84
     autocollant
    -0.83
    POSITIVE LOGITS
    '
    0.75
     can
    0.71
     I
    0.71
     θα
    0.67
     is
    0.66
     F
    0.65
    </b>
    0.65
     N
    0.64
     μην
    0.62
    ’
    0.62
    Activations Density 0.015%

    No Known Activations