© 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. 12050
    Prev
    Next
    INDEX
    Explanations

    references to the process of generating or developing new ideas or plans

    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
    abestanden
    -0.72
     GenerationType
    -0.71
     متعلقه
    -0.70
    }")]
    -0.69
    expandindo
    -0.68
    примеча
    -0.67
    Билгалдахарш
    -0.66
     препратки
    -0.66
    adaptiveStyles
    -0.65
     مرئيه
    -0.65
    POSITIVE LOGITS
     conception
    3.20
     Conception
    2.33
     conceptions
    2.25
    conception
    2.08
    Conception
    2.05
     concepción
    1.58
     conceive
    1.26
     concep
    1.22
     conceived
    1.16
     conce
    0.81
    Activations Density 0.016%

    No Known Activations