© 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. 28384
    Prev
    Next
    INDEX
    Explanations

    references to academic titles and positions, specifically regarding professors

    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
     skippy
    -0.77
    hintText
    -0.77
    EndContext
    -0.76
     Offisielt
    -0.75
     techniczne
    -0.72
     Rite
    -0.72
     ſche
    -0.72
     eletrônico
    -0.70
     saveiro
    -0.68
    ymi
    -0.68
    POSITIVE LOGITS
     professors
    1.22
     professor
    1.13
     Professor
    1.11
     Professors
    1.08
    Professor
    1.05
    professor
    1.02
     Prof
    0.96
     PROFESSOR
    0.95
     PROF
    0.94
    教授
    0.91
    Activations Density 0.008%

    No Known Activations