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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14101
    Prev
    Next
    INDEX
    Explanations

    references to legal guilt or innocence in the context of criminal cases

    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
    ThroughAttribute
    -0.87
     MenuView
    -0.77
    ItemBackground
    -0.76
    GEBURTSDATUM
    -0.75
    VersionUID
    -0.72
    ViewFeatures
    -0.69
    esez
    -0.68
    complexType
    -0.67
     Signalez
    -0.67
     समीक्षाएं
    -0.67
    POSITIVE LOGITS
     guilt
    2.86
     Guilt
    2.09
     guil
    0.93
     remorse
    0.67
     Schuld
    0.67
    ilt
    0.53
    疚
    0.52
     shame
    0.49
     regret
    0.48
    ILT
    0.48
    Activations Density 0.001%

    No Known Activations