© 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. 2-RES-MATRYOSHKA-DC
    7. 6712
    Prev
    Next
    INDEX
    Explanations

    expressions of hope or optimistic sentiment

    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
    __':
    -0.82
    __':
    -0.75
     imper
    -0.73
    __":
    -0.69
    gameserver
    -0.68
    Aff
    -0.63
    __":
    -0.63
    hyrchwyd
    -0.59
    XmlAccessType
    -0.59
    Autoritní
    -0.58
    POSITIVE LOGITS
     hope
    3.45
     Hope
    3.13
    Hope
    3.11
    hope
    2.98
     HOPE
    2.89
     hopes
    2.70
     hoped
    2.56
    HOPE
    2.47
     hoping
    2.33
     Hopes
    2.31
    Activations Density 0.018%

    No Known Activations