© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6578
    Prev
    Next
    INDEX
    Explanations

    terms related to objectivity in assessments and evaluations

    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
    Negative Logits
    ness
    -0.63
    </em>
    -0.57
     Great
    -0.55
     Pless
    -0.54
    ...
    -0.54
    TagMode
    -0.54
    LEAN
    -0.54
    —
    -0.54
    +:+
    -0.53
    "—
    -0.52
    POSITIVE LOGITS
     Objective
    1.25
     OBJECTIVE
    1.25
     objective
    1.21
    Objective
    1.21
    OBJECTIVE
    1.20
     Objectives
    1.20
    objective
    1.20
     objectives
    1.19
    objectives
    1.16
     objectively
    1.15
    Activations Density 0.030%

    No Known Activations