© 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. 1-RES-MATRYOSHKA-DC
    7. 755
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and qualities

    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
    adaptiveStyles
    -0.74
    ########.
    -0.60
    StructEnd
    -0.59
    mtrl
    -0.58
    PerformLayout
    -0.56
    dafx
    -0.56
    +:+
    -0.56
    Voci
    -0.53
    发表于
    -0.51
     ProtoMessage
    -0.51
    POSITIVE LOGITS
     personal
    5.03
    personal
    4.66
     Personal
    4.56
    Personal
    4.56
     PERSONAL
    4.19
    PERSONAL
    3.94
     personales
    3.41
     personally
    3.28
     persönliche
    3.19
     personnelle
    3.11
    Activations Density 0.061%

    No Known Activations