© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13060
    Prev
    Next
    INDEX
    Explanations

    references to a specific neural weakness or vulnerability

    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
    rungsseite
    -0.91
    ftagPool
    -0.90
    
    -0.71
     Poor
    -0.60
     POOR
    -0.59
     HasFactory
    -0.58
    
    -0.58
    multirow
    -0.57
    principalTable
    -0.57
     auguri
    -0.57
    POSITIVE LOGITS
     weakness
    2.81
     Weakness
    2.30
     weaknesses
    2.02
    Weakness
    1.82
     debilidad
    1.70
    Weaknesses
    1.05
    弱点
    0.93
     Schwä
    0.89
     drawback
    0.77
    缺點
    0.76
    Activations Density 0.001%

    No Known Activations