© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15866
    Prev
    Next
    INDEX
    Explanations

    expressions of dissatisfaction or frustration

    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
     facing
    -0.81
    NUMX
    -0.75
     faces
    -0.75
    LLocation
    -0.75
     faced
    -0.71
    AnchorStyles
    -0.71
     Facing
    -0.70
    Facing
    -0.67
    StoryboardSegue
    -0.66
     Audiodateien
    -0.62
    POSITIVE LOGITS
    face
    1.77
    FACE
    1.39
    Face
    1.16
     Face
    0.75
     useAppContext
    0.63
    inigte
    0.59
     ''}
    0.59
    Pyx
    0.59
     FACE
    0.58
    legung
    0.57
    Activations Density 0.001%

    No Known Activations