© 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. 0-RES-MATRYOSHKA-DC
    7. 11498
    Prev
    Next
    INDEX
    Explanations

    references to dolphin-related content, particularly highlighting the term "dolphin" and related words

    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
    __":
    -0.69
    $_['
    -0.66
    __":
    -0.65
    roidered
    -0.64
    <?
    -0.63
    ]-->
    -0.63
    ']):
    -0.60
    SPATH
    -0.59
    ({_
    -0.59
    quelize
    -0.58
    POSITIVE LOGITS
    Aware
    0.88
    ofan
    0.85
     parla
    0.82
    aware
    0.75
     dolphin
    0.72
    alous
    0.69
     Hancock
    0.68
    cg
    0.68
     dolphins
    0.67
     Dolphin
    0.64
    Activations Density 0.018%

    No Known Activations