© 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. 12-RES-MATRYOSHKA-DC
    7. 23799
    Prev
    Next
    INDEX
    Explanations

    terms related to mentorship and educational relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     special
    -0.58
     saa
    -0.54
     Jarvis
    -0.54
    깥
    -0.54
     Caro
    -0.52
    リス
    -0.51
     dets
    -0.51
     Moss
    -0.50
    DIM
    -0.50
    DispatchToProps
    -0.50
    POSITIVE LOGITS
     mentor
    1.59
     mentors
    1.50
     mentoring
    1.48
     Mentor
    1.47
     mentorship
    1.45
     Mentoring
    1.39
    Mentor
    1.35
    mentor
    1.25
     Ment
    1.20
    Ment
    1.09
    Activations Density 0.002%

    No Known Activations