© 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. 7240
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly focusing on the pronoun "her" and related personal references

    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
     ་་
    -0.91
     themſelves
    -0.88
     yourselves
    -0.85
     Jefus
    -0.84
     doubtnut
    -0.82
     Shakspeare
    -0.82
     ausgesch
    -0.81
     ſche
    -0.80
     poffible
    -0.79
     unſ
    -0.77
    POSITIVE LOGITS
     her
    2.52
    her
    1.91
     Her
    1.66
    Her
    1.63
     HER
    1.59
    HER
    1.38
     ее
    1.03
    她的
    1.03
     haar
    0.94
     её
    0.91
    Activations Density 0.084%

    No Known Activations