© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 368
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and descriptors that convey appreciation or encouragement

    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
     المعيارى
    -0.76
     فريبيس
    -0.73
     AspNetCore
    -0.71
    ScopeManager
    -0.67
    PathVariable
    -0.67
    osoba
    -0.65
    InjectMocks
    -0.64
    =$((
    -0.63
    SequentialGroup
    -0.59
    terase
    -0.57
    POSITIVE LOGITS
     good
    1.04
    good
    0.99
     bagus
    0.96
     excellent
    0.90
    excellent
    0.86
     splendid
    0.85
     nice
    0.83
    endid
    0.82
     wonderful
    0.82
     GOOD
    0.81
    Activations Density 3.423%

    No Known Activations