© 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. 2823
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating a preference for "rather than" and "more than" constructions

    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
     steeper
    -0.71
    })`
    -0.65
     Cheaper
    -0.63
    CodeAttribute
    -0.62
     houſe
    -0.60
     minori
    -0.60
     minore
    -0.60
     Menor
    -0.60
    ]`
    -0.59
     Brasileiro
    -0.58
    POSITIVE LOGITS
    iastes
    0.66
     nearly
    0.64
    aderie
    0.59
     almost
    0.56
    äher
    0.56
    OPSIS
    0.55
    setCancelable
    0.54
     közel
    0.54
    oltre
    0.53
    nearly
    0.53
    Activations Density 0.044%

    No Known Activations